© 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. 22600
    Prev
    Next
    INDEX
    Explanations

    dates related to significant historical events

    oai_token-act-pair · gpt-3.5-turbo

    references to the September 11 attacks and related events

    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
     scoop
    -0.81
     Distribut
    -0.64
    ãĤ¨ãĥ«
    -0.63
     marqu
    -0.63
    xxxxxxxx
    -0.60
    abase
    -0.59
     vit
    -0.59
     DI
    -0.58
    ryce
    -0.58
    ITH
    -0.58
    POSITIVE LOGITS
    roth
    0.85
    ools
    0.75
     Attacks
    0.74
    interstitial
    0.71
    kefeller
    0.70
    Downloadha
    0.69
     Harbor
    0.68
    warts
    0.68
     Janeiro
    0.67
    oral
    0.66
    Activations Density 0.075%

    No Known Activations