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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9-RES-JB
    6. 2085
    Prev
    Next
    INDEX
    Explanations

    pronouns and proper nouns of people's names

    oai_token-act-pair · gpt-3.5-turbo

    subjective statements and personal opinions within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wcsstore
    -0.73
     actionGroup
    -0.71
    rocket
    -0.66
     Portable
    -0.64
    clone
    -0.63
    ulla
    -0.62
    album
    -0.62
     guiActiveUnfocused
    -0.60
    eful
    -0.59
    usha
    -0.59
    POSITIVE LOGITS
     reasoned
    1.19
     argued
    1.11
     argues
    1.07
     said
    1.04
     contended
    1.01
     says
    1.01
     contends
    0.95
     asserted
    0.94
     argue
    0.92
     explained
    0.92
    Activations Density 0.211%

    No Known Activations