© 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. 1532
    Prev
    Next
    INDEX
    Explanations

    queries involving specific criteria or coding instructions

    oai_token-act-pair · gpt-3.5-turbo

    elements related to data analysis or technical processes

    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
    ↵
    -1.25
    SPONSORED
    -1.14
    <|endoftext|>
    -0.92
    ↵↵
    -0.89
    etheless
    -0.86
    ADVERTISEMENT
    -0.67
    Advertisements
    -0.65
     respectively
    -0.65
    ↵Âł
    -0.65
    ancial
    -0.64
    POSITIVE LOGITS
     Pastebin
    0.67
     guiName
    0.65
     partName
    0.64
    ãĤ¼ãĤ¦ãĤ¹
    0.64
     LV
    0.63
     Tradable
    0.61
     (?,
    0.58
    ãģ¯
    0.56
     à¨
    0.55
     Mahjong
    0.55
    Activations Density 0.592%

    No Known Activations