© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 13471
    Prev
    Next
    INDEX
    Explanations

    proper nouns and organizations

    oai_token-act-pair · gpt-3.5-turbo

    combinations of punctuation and specific words, indicating a focus on lists or enumerations

    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
    nih
    -0.74
    osc
    -0.71
    anya
    -0.65
    lift
    -0.64
    ocalypse
    -0.64
    anski
    -0.64
    animate
    -0.62
    oscopic
    -0.62
    aven
    -0.61
    ãĥ¥
    -0.60
    POSITIVE LOGITS
     meanwhile
    1.07
     flanked
    0.88
     accompanied
    0.83
     however
    0.82
     citing
    0.82
     alas
    0.81
     fearing
    0.81
     backed
    0.81
     unsurprisingly
    0.78
     albeit
    0.73
    Activations Density 0.291%

    No Known Activations