© 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. 9-RES-JB
    11. 1035
    Prev
    Next
    INDEX
    Explanations

    URLs or email addresses

    oai_token-act-pair · gpt-3.5-turbo

    URLs and email addresses

    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
     Maher
    -0.86
     Rye
    -0.79
     Jihad
    -0.78
     tabloid
    -0.77
     refrain
    -0.76
     Krugman
    -0.75
     tongue
    -0.75
     sequence
    -0.74
     bitterness
    -0.73
     tease
    -0.72
    POSITIVE LOGITS
    english
    1.41
    facebook
    1.40
    events
    1.30
    cit
    1.28
    gp
    1.24
    www
    1.23
    global
    1.22
    south
    1.19
    john
    1.18
    gmail
    1.17
    Activations Density 0.093%

    No Known Activations