© 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. 14114
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific physical locations or directions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or points in a discussion or analysis

    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
    uthor
    -0.86
    ÄŁ
    -0.78
    soever
    -0.68
    ESE
    -0.68
    OOL
    -0.68
    catentry
    -0.66
    ISM
    -0.64
     Sut
    -0.64
    ctr
    -0.63
    ÃįÃį
    -0.62
    POSITIVE LOGITS
    lessly
    1.09
    blank
    0.95
     Reyes
    0.92
    edly
    0.90
     blank
    0.89
    pointers
    0.77
    point
    0.75
    lessness
    0.75
     deduction
    0.75
    finder
    0.73
    Activations Density 0.050%

    No Known Activations