© 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. 11-RES-JB
    11. 24545
    Prev
    Next
    INDEX
    Explanations

    involved parties in a research setting such as participants and respondents

    oai_token-act-pair · gpt-3.5-turbo

    references to survey or study participants and respondents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bound
    -0.77
     slic
    -0.67
    alde
    -0.65
    YP
    -0.65
    aceous
    -0.64
    tesy
    -0.64
    cer
    -0.64
     Sparrow
    -0.63
    unct
    -0.62
    APD
    -0.62
    POSITIVE LOGITS
    hip
    0.96
    hips
    0.92
    '
    0.91
     surn
    0.81
    ']
    0.80
     who
    0.79
    ele
    0.73
    '/
    0.73
    who
    0.72
     WHO
    0.71
    Activations Density 0.166%

    No Known Activations