© 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. 6-RES-JB
    11. 18458
    Prev
    Next
    INDEX
    Explanations

    IP addresses and related technical strings

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and references related to transactions or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     signs
    -0.58
     icing
    -0.56
    natureconservancy
    -0.54
     Satanic
    -0.52
     mend
    -0.51
    onite
    -0.51
    aminer
    -0.50
     sad
    -0.50
    asty
    -0.50
     soap
    -0.50
    POSITIVE LOGITS
    fram
    0.63
    renheit
    0.62
    cloud
    0.59
    =$
    0.56
    Reviewed
    0.56
    quad
    0.54
    Catal
    0.53
    ipel
    0.52
    cffff
    0.52
    strip
    0.51
    Activations Density 0.450%

    No Known Activations