© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 39593
    Prev
    Next
    INDEX
    Explanations

    academic or technical terms and subjects, likely related to information technology or educational contexts

    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
    55
    +0.10
    0.6%
    656
    +0.08
    0.5%
    605
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    656
    +0.10
    0.08
    697
    +0.08
    0.06
    55
    +0.08
    0.12
    Negative Logits
    lessly
    -0.63
    inition
    -0.57
     Cosponsors
    -0.56
    */(
    -0.55
    gence
    -0.54
    Services
    -0.54
    byn
    -0.52
    atories
    -0.52
    glers
    -0.50
    cases
    -0.50
    POSITIVE LOGITS
    pling
    0.75
    qua
    0.72
    iba
    0.68
    pler
    0.66
    âĶĢâĶĢâĶĢâĶĢ
    0.63
    pered
    0.62
    hedral
    0.62
    bay
    0.60
    plin
    0.59
    pled
    0.59
    Activations Density 8.763%

    No Known Activations