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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14883
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific names with capitalized letters

    oai_token-act-pair · gpt-3.5-turbo

    acronyms and abbreviated terms, particularly those related to titles or organizations

    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
    iw
    -0.82
    iol
    -0.81
    iaz
    -0.76
    IK
    -0.75
    igun
    -0.74
    javascript
    -0.73
    CIA
    -0.72
    IO
    -0.71
     Bian
    -0.71
    423
    -0.71
    POSITIVE LOGITS
    st
    0.92
    sts
    0.86
    thirds
    0.85
    geist
    0.83
    ends
    0.80
     Subst
    0.78
    end
    0.78
     subst
    0.78
     Ost
    0.77
    unda
    0.75
    Activations Density 0.332%

    No Known Activations