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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 12441
    Prev
    Next
    INDEX
    Explanations

    specific mentions of "Ars" or "Arsenal"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a specific entity or organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ³
    -0.75
    ugg
    -0.74
    iol
    -0.73
    itory
    -0.71
    roid
    -0.69
     Diver
    -0.67
     Mau
    -0.67
    utton
    -0.67
    ope
    -0.67
     Nurse
    -0.67
    POSITIVE LOGITS
     Ars
    1.81
     motors
    1.37
     Americas
    1.33
     Ps
    1.31
     Ans
    1.31
     Ips
    1.30
     RS
    1.27
     Wester
    1.23
     antis
    1.19
     Ames
    1.12
    Activations Density 0.050%

    No Known Activations