© 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. 1-RES-JB
    11. 20132
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names

    oai_token-act-pair · gpt-3.5-turbo

    the name "Kirk" and its associated context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */(
    -0.83
    ĻĤ
    -0.77
    abuse
    -0.76
    legraph
    -0.73
    ntil
    -0.72
     receptive
    -0.72
     outgoing
    -0.71
    ittee
    -0.70
    ccording
    -0.69
    uctor
    -0.66
    POSITIVE LOGITS
    patrick
    1.45
     Kirk
    1.17
     Cousins
    0.93
    bys
    0.90
    lands
    0.90
    sey
    0.86
     Hamm
    0.86
    STON
    0.84
    lake
    0.83
    wall
    0.83
    Activations Density 0.003%

    No Known Activations