Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 34001
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives related to conditions or qualities encountered in various situations

    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
    +0.10
    0.5%
    569
    +0.09
    0.5%
    277
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.10
    0.13
    288
    +0.09
    0.23
    251
    +0.08
    0.10
    Negative Logits
    encer
    -0.67
    apego
    -0.65
    apter
    -0.63
    auga
    -0.61
    ndra
    -0.61
    vous
    -0.60
    gemony
    -0.58
    xit
    -0.58
    ramid
    -0.58
    uristic
    -0.58
    POSITIVE LOGITS
     increments
    0.98
     proportions
    0.94
     situations
    0.87
     quantities
    0.84
     places
    0.82
     terms
    0.81
     circumstances
    0.81
     fashion
    0.80
     circles
    0.80
     amounts
    0.78
    Activations Density 9.823%

    No Known Activations