© 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. 4-RES-JB
    11. 3728
    Prev
    Next
    INDEX
    Explanations

    terms related to information technology (IT)

    oai_token-act-pair · gpt-3.5-turbo

    references to information technology and related concepts

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

    No Comments

    Negative Logits
    ãĥ©ãĥ³
    -0.82
    EStream
    -0.72
    ãĤ£
    -0.69
    fed
    -0.69
    shown
    -0.67
    ¥ŀ
    -0.67
    warning
    -0.64
     conjecture
    -0.63
     Strait
    -0.63
    wcs
    -0.62
    POSITIVE LOGITS
    TY
    1.02
    IME
    1.00
    ELY
    0.92
    LIN
    0.91
    chen
    0.91
    aylor
    0.91
    LER
    0.90
    MIN
    0.90
    UAL
    0.89
    ALS
    0.88
    Activations Density 0.009%

    No Known Activations