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. 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. 7836
    Prev
    Next
    INDEX
    Explanations

    exclamatory statements and expressions of strong agreement

    oai_token-act-pair · gpt-3.5-turbo

    affirmative or definitive statements in conversations

    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
    ]);
    -0.80
    arted
    -0.70
    ]).
    -0.69
    éĹĺ
    -0.68
    '."
    -0.64
    hover
    -0.62
    anwhile
    -0.62
    '>
    -0.61
    pered
    -0.61
    }}
    -0.59
    POSITIVE LOGITS
    laughs
    1.08
     definitely
    0.94
     answer
    0.94
     depends
    0.87
    Laughs
    0.85
    initely
    0.83
     certainly
    0.80
    laughter
    0.79
     absolutely
    0.76
     anecd
    0.76
    Activations Density 0.452%

    No Known Activations