© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2415
    Prev
    Next
    INDEX
    Explanations

    actions involving movement or positioning words

    oai_token-act-pair · gpt-3.5-turbo

    actions involving upward and downward movement or orientation

    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
    insula
    -0.71
     moderation
    -0.65
    ufact
    -0.63
    ivery
    -0.63
     Membership
    -0.62
    cially
    -0.61
    CLUD
    -0.61
    nit
    -0.60
    BuyableInstoreAndOnline
    -0.59
    UFF
    -0.58
    POSITIVE LOGITS
     momentarily
    0.90
     uncontroll
    0.90
    wards
    0.88
     clutching
    0.87
     waving
    0.86
     violently
    0.84
     angrily
    0.84
     frantically
    0.83
     awkwardly
    0.83
     curled
    0.82
    Activations Density 0.278%

    No Known Activations