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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 45301
    Prev
    Next
    INDEX
    Explanations

    terms related to dogs

    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
    +0.20
    0.9%
    76
    +0.14
    0.6%
    167
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.20
    0.09
    76
    +0.14
    0.08
    652
    +0.13
    0.05
    Negative Logits
    éĹĺ
    -0.92
    itures
    -0.81
    erences
    -0.80
    esson
    -0.80
    artz
    -0.79
    oulos
    -0.79
     Edison
    -0.79
    farious
    -0.79
    DERR
    -0.79
    icity
    -0.77
    POSITIVE LOGITS
    matic
    1.11
    fight
    1.11
    patch
    1.11
    matically
    1.08
    fights
    1.07
    fighting
    1.05
    meat
    1.04
     barking
    1.02
    fighter
    1.02
    gie
    1.01
    Activations Density 7.598%

    No Known Activations