© 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. 10-RES-JB
    11. 9989
    Prev
    Next
    INDEX
    Explanations

    quotes or statements made by spokespeople

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "said" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BILL
    -0.74
    ocaust
    -0.73
    pee
    -0.73
    estern
    -0.71
    peg
    -0.70
    illions
    -0.70
    erella
    -0.68
    à¦
    -0.68
    ãĥĻ
    -0.67
    amus
    -0.66
    POSITIVE LOGITS
     "(
    0.89
    :"
    0.85
     "[
    0.84
    :
    0.81
     neither
    0.81
     investigators
    0.80
     there
    0.78
     inquiries
    0.76
     unspecified
    0.75
    :'
    0.74
    Activations Density 0.132%

    No Known Activations