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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 125
    Prev
    Next
    INDEX
    Explanations

    the word "dodge" or its present participle form "dodging"

    oai_token-act-pair · gpt-4-turbo

    verbs related to avoiding or escaping a situation

    oai_token-act-pair · gpt-3.5-turbo

    words associated with evading or avoiding responsibilities and obligations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onial
    -0.76
    sat
    -0.76
    oyal
    -0.71
     antioxid
    -0.69
     Institution
    -0.68
    imen
    -0.68
    itar
    -0.68
    aster
    -0.68
     Grizz
    -0.63
    apsed
    -0.63
    POSITIVE LOGITS
     dodge
    1.29
     dodging
    1.15
     evasion
    1.01
     evade
    0.99
     deflect
    0.86
     dodged
    0.84
     dod
    0.81
    asive
    0.79
     avoidance
    0.76
    poke
    0.76
    Activations Density 0.021%

    No Known Activations