© 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. 10-RES-JB
    11. 2639
    Prev
    Next
    INDEX
    Explanations

    digital object identifiers (DOIs) within references

    oai_token-act-pair · gpt-3.5-turbo

    scientific references and citation information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    steen
    -0.71
    adiq
    -0.66
    HUD
    -0.65
     Beard
    -0.62
     Advocate
    -0.62
    tein
    -0.59
     Cutter
    -0.59
     Restaur
    -0.58
    seless
    -0.58
     decor
    -0.57
    POSITIVE LOGITS
    doi
    1.34
     doi
    1.20
     DOI
    1.17
    Abstract
    0.99
     dx
    0.97
    dx
    0.97
     pdf
    0.90
     Neuroscience
    0.86
    pdf
    0.86
     Abstract
    0.85
    Activations Density 0.024%

    No Known Activations