© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 9486
    Prev
    Next
    INDEX
    Explanations

    numbers representing prices or amounts of money

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific monetary value of 95 USD

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phas
    -0.82
    gie
    -0.77
    suit
    -0.74
    wards
    -0.74
    iard
    -0.73
    geist
    -0.71
    gewater
    -0.70
    gon
    -0.69
    izen
    -0.68
    pressure
    -0.68
    POSITIVE LOGITS
     ILCS
    1.03
    %:
    0.81
    RET
    0.74
    liest
    0.71
    678
    0.71
    arser
    0.71
    isher
    0.70
    ãĥ¼ãĥĨ
    0.70
    olini
    0.69
     Patton
    0.68
    Activations Density 0.046%

    No Known Activations