© 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. 4-RES-JB
    11. 18371
    Prev
    Next
    INDEX
    Explanations

    rankings or positions in a list

    oai_token-act-pair · gpt-3.5-turbo

    rankings or numerical achievements associated with entities or individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utic
    -0.76
    atan
    -0.75
    apers
    -0.74
    ili
    -0.71
    rots
    -0.71
    ét
    -0.70
    allah
    -0.68
    ãĥĨãĤ£
    -0.67
    eks
    -0.66
    acas
    -0.65
    POSITIVE LOGITS
     loader
    0.89
     inhibitor
    0.77
     priority
    0.74
     contender
    0.68
    rower
    0.67
     inhibitors
    0.66
     spons
    0.65
     dime
    0.65
    /#
    0.65
     cornerback
    0.63
    Activations Density 0.021%

    No Known Activations