© 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. 17976
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to a specific person's name, "Barack"

    oai_token-act-pair · gpt-3.5-turbo

    repeated instances of a specific name or term

    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
    senal
    -0.80
     conflic
    -0.78
     eleph
    -0.73
    ĻĤ
    -0.71
     Debor
    -0.69
    olith
    -0.68
     reckoning
    -0.66
     livest
    -0.66
     tradem
    -0.64
     trem
    -0.63
    POSITIVE LOGITS
    ack
    1.23
    enzie
    1.12
    acks
    1.11
    ACK
    1.09
    ademic
    0.99
    acked
    0.98
    intosh
    0.93
    les
    0.91
    ansas
    0.89
    ernel
    0.88
    Activations Density 0.009%

    No Known Activations