© 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. 9-RES-JB
    11. 1382
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Birmingham" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bir" and its variations, as well as related names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eur
    -0.84
    ĺħ
    -0.64
    Desk
    -0.60
    ĵĺ
    -0.57
    ographers
    -0.56
     Narc
    -0.56
     nomine
    -0.55
    rained
    -0.55
    iates
    -0.55
     Harmon
    -0.55
    POSITIVE LOGITS
    mingham
    1.33
    thing
    1.13
    git
    1.05
    ging
    0.97
    acial
    0.96
    keley
    0.92
    chall
    0.92
    cling
    0.90
    ks
    0.89
    gence
    0.88
    Activations Density 0.056%

    No Known Activations