© 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. 23489
    Prev
    Next
    INDEX
    Explanations

    Twitter usernames and names mentioned in tweets

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals or celebrities

    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
     installations
    -0.68
    rontal
    -0.68
     inheritance
    -0.64
     outings
    -0.63
     setting
    -0.63
     exhibits
    -0.62
     worrying
    -0.61
     playable
    -0.60
     intimidating
    -0.60
     garment
    -0.60
    POSITIVE LOGITS
     (@
    1.83
     âľ
    1.00
     ðŁ
    0.97
     Ù
    0.93
     âĻ
    0.91
     âĿ
    0.88
     Ø
    0.84
     âĺ
    0.82
    ðŁ
    0.81
    âľ
    0.80
    Activations Density 0.151%

    No Known Activations