© 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. 20149
    Prev
    Next
    INDEX
    Explanations

    names with the letters "itt" and prioritizes a specific value of 9

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named "itt."

    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
    ĸļ
    -0.71
    ©¶æ
    -0.69
     arteries
    -0.65
     graves
    -0.65
    ħĭ
    -0.65
    ģ«
    -0.64
     captivity
    -0.63
     Horus
    -0.62
     NCT
    -0.61
    EStream
    -0.60
    POSITIVE LOGITS
    sburgh
    1.57
    itt
    1.30
    ype
    0.99
    omo
    0.97
    enger
    0.97
    oyd
    0.94
    leness
    0.91
    onen
    0.90
    orno
    0.89
    sburg
    0.88
    Activations Density 0.009%

    No Known Activations