© 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. 3-RES-JB
    11. 15245
    Prev
    Next
    INDEX
    Explanations

    Roman numerals with the value of 3

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific topic or subject labeled as "III"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sym
    -0.76
    pal
    -0.75
    locks
    -0.72
    numbered
    -0.71
    entary
    -0.69
    bear
    -0.68
    staking
    -0.68
    circ
    -0.67
    partisan
    -0.67
    oard
    -0.65
    POSITIVE LOGITS
    rd
    1.54
    RD
    0.86
    imilation
    0.78
    ochet
    0.76
    imus
    0.75
    rees
    0.75
    hered
    0.75
    endez
    0.72
    hetti
    0.71
    rade
    0.71
    Activations Density 0.059%

    No Known Activations