© 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. 8-RES-JB
    11. 6370
    Prev
    Next
    INDEX
    Explanations

    proper nouns and associated organizations or titles

    oai_token-act-pair · gpt-3.5-turbo

    instances of punctuation, particularly periods in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stray
    -0.72
     dips
    -0.69
     indul
    -0.68
     achievable
    -0.67
    riet
    -0.67
    urance
    -0.66
    izoph
    -0.65
     fleeting
    -0.65
     ballpark
    -0.65
    pees
    -0.64
    POSITIVE LOGITS
     His
    1.18
     Together
    1.18
     Both
    1.15
     He
    1.15
     She
    1.14
     Likewise
    1.14
     Similarly
    1.10
     Her
    1.07
     Previously
    1.05
     Others
    1.03
    Activations Density 0.637%

    No Known Activations