© 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. 20332
    Prev
    Next
    INDEX
    Explanations

    references to size or measurement

    oai_token-act-pair · gpt-3.5-turbo

    references to measurement or scale

    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
    esson
    -0.82
    eering
    -0.77
    vous
    -0.72
    odore
    -0.71
     Leilan
    -0.71
    eers
    -0.68
    ËĪ
    -0.68
    toc
    -0.68
    ĪĴ
    -0.68
    ournal
    -0.67
    POSITIVE LOGITS
     scale
    0.89
     invari
    0.82
     replica
    0.82
     scales
    0.77
     magnification
    0.75
    Factor
    0.75
     fabrication
    0.74
     heights
    0.72
    Scale
    0.71
    scale
    0.71
    Activations Density 0.027%

    No Known Activations