© 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. 8-RES-JB
    11. 18494
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming and technical details like function prototypes, processor statements, keys, blocks, identifiers, and more

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to programming and data management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oÄŁ
    -0.76
     unden
    -0.71
    GoldMagikarp
    -0.69
    Args
    -0.67
    Synopsis
    -0.66
    ãĥį
    -0.65
    Buzz
    -0.64
    ãĤ¨ãĥ«
    -0.64
    PDATE
    -0.63
    REF
    -0.63
    POSITIVE LOGITS
    etting
    1.43
    hips
    1.38
    mith
    1.38
    paces
    1.38
    pace
    1.36
    hip
    1.31
    heet
    1.22
    poons
    1.17
    cale
    1.12
    pring
    1.10
    Activations Density 0.514%

    No Known Activations