© 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. 0-RES-JB
    11. 1122
    Prev
    Next
    INDEX
    Explanations

    names or words related to specific locations, possibly with Arabic or Middle Eastern influence

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of capability or ability

    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
     Sun
    -0.65
     Hans
    -0.61
     POST
    -0.58
     trace
    -0.58
     GE
    -0.57
     Gina
    -0.57
     forcing
    -0.57
     header
    -0.57
     DO
    -0.56
     spacecraft
    -0.55
    POSITIVE LOGITS
    abl
    4.82
    abil
    1.71
    abul
    1.59
    ability
    1.36
    abilities
    1.34
    ably
    1.26
    ibl
    1.17
    ab
    1.16
    ables
    1.13
    ABLE
    1.10
    Activations Density 0.016%

    No Known Activations