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. 7-RES-JB
    6. 13119
    Prev
    Next
    INDEX
    Explanations

    proper nouns or entities such as names of people, places, or organizations

    oai_token-act-pair · gpt-3.5-turbo

    articles and determiners (such as "a" and "an") preceding nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilty
    -0.91
    oper
    -0.83
    anism
    -0.83
    INO
    -0.78
    abilities
    -0.75
    alties
    -0.75
    Own
    -0.74
    Hon
    -0.74
    Avoid
    -0.73
    oots
    -0.71
    POSITIVE LOGITS
     flurry
    0.91
     mysterious
    0.89
     bombshell
    0.88
     spate
    0.85
     slew
    0.85
     group
    0.83
     woman
    0.82
     handful
    0.82
     gunman
    0.81
     commenter
    0.81
    Activations Density 0.187%

    No Known Activations