© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 33961
    Prev
    Next
    INDEX
    Explanations

    text related to technical aspects of software development and computer systems

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.09
    0.5%
    396
    +0.09
    0.5%
    479
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    517
    +0.09
    0.09
    188
    +0.09
    0.08
    564
    +0.08
    0.08
    Negative Logits
    pload
    -0.73
    arth
    -0.70
    alus
    -0.58
    arov
    -0.57
    wright
    -0.57
    esville
    -0.56
    oother
    -0.55
    wood
    -0.54
    oleon
    -0.54
    pour
    -0.53
    POSITIVE LOGITS
     equivalents
    0.65
     interface
    0.63
     integrity
    0.62
     condemnation
    0.61
     interaction
    0.59
     perspective
    0.58
     continuum
    0.56
     disruptions
    0.55
     versions
    0.55
     behavior
    0.55
    Activations Density 6.850%

    No Known Activations