© 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. 6-RES-JB
    11. 855
    Prev
    Next
    INDEX
    Explanations

    the numerical values that follow the phrase "A total of"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that quantify totals or counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Males
    -0.68
    era
    -0.65
    Matrix
    -0.62
    hend
    -0.62
    webkit
    -0.58
    acus
    -0.57
     Presence
    -0.57
    tera
    -0.56
    itute
    -0.56
     Receiver
    -0.55
    POSITIVE LOGITS
     seventy
    0.76
     eighty
    0.76
     eight
    0.76
     seven
    0.75
     six
    0.73
     sixty
    0.72
     nine
    0.71
     twelve
    0.70
     eighteen
    0.69
     thirteen
    0.69
    Activations Density 0.052%

    No Known Activations