© 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. 35132
    Prev
    Next
    INDEX
    Explanations

    information related to smartphone models and technology updates

    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
    +0.15
    0.8%
    288
    +0.14
    0.7%
    351
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.18
    326
    +0.14
    0.18
    232
    +0.08
    0.06
    Negative Logits
    cies
    -0.77
    unct
    -0.71
    nels
    -0.70
    pard
    -0.70
    ichita
    -0.70
    esty
    -0.68
     estab
    -0.68
    ricks
    -0.68
    ermanent
    -0.67
    vironment
    -0.65
    POSITIVE LOGITS
     Galaxy
    0.91
     Nexus
    0.70
     Apps
    0.66
     Shades
    0.66
     Sabha
    0.65
     Note
    0.65
    izoph
    0.65
    axy
    0.65
     Launch
    0.64
    plane
    0.63
    Activations Density 6.125%

    No Known Activations