© 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. 6683
    Prev
    Next
    INDEX
    Explanations

    times of day in a specific format (e.g., 9 a.m.)

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 'a' in 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
     ank
    -0.58
    ahime
    -0.55
     wrists
    -0.54
     unavoid
    -0.53
     Insurance
    -0.53
     newcom
    -0.52
     eyes
    -0.52
     forwards
    -0.52
     acknowled
    -0.52
     analogue
    -0.51
    POSITIVE LOGITS
    .,
    0.88
    .;
    0.79
    .,"
    0.79
    .?
    0.76
    .),
    0.75
    clock
    0.71
    pm
    0.68
    ._
    0.67
    versions
    0.66
    ./
    0.65
    Activations Density 0.013%

    No Known Activations