© 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. 15192
    Prev
    Next
    INDEX
    Explanations

    words related to specific terms and concepts, such as "ultimate", "Indeed", and "Why"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific sports and the excitement they generate

    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
    NetMessage
    -0.72
    taboola
    -0.70
    actionDate
    -0.66
    iHUD
    -0.66
    eatures
    -0.65
    natureconservancy
    -0.63
     Azerb
    -0.63
    Interstitial
    -0.61
    parency
    -0.61
    ©¶æ¥µ
    -0.60
    POSITIVE LOGITS
    utils
    0.58
    horn
    0.56
     payable
    0.54
     grou
    0.54
    hot
    0.53
     helper
    0.53
    cour
    0.53
     holder
    0.53
     packages
    0.52
    ser
    0.52
    Activations Density 0.669%

    No Known Activations