© 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. 6665
    Prev
    Next
    INDEX
    Explanations

    phrases indicating widespread or global occurrences

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate prevalence or occurrence across various contexts

    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
    ãĤº
    -0.76
    ially
    -0.67
    acles
    -0.67
    ascript
    -0.66
    Password
    -0.65
    emis
    -0.63
    eln
    -0.63
    uary
    -0.62
    uers
    -0.62
    resy
    -0.62
    POSITIVE LOGITS
     again
    0.96
     town
    0.89
     campus
    0.83
     Europe
    0.83
    roads
    0.77
    lake
    0.76
    earth
    0.70
     AMERICA
    0.70
     Again
    0.69
    again
    0.69
    Activations Density 0.029%

    No Known Activations