© 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. 1-RES-JB
    11. 808
    Prev
    Next
    INDEX
    Explanations

    numerical values in a specific format, such as "86" or "86.9"

    oai_token-act-pair · gpt-3.5-turbo

    the repeated identification of the numeric sequence "86" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.78
    */(
    -0.73
    rha
    -0.73
     citiz
    -0.71
    rouch
    -0.71
     mosqu
    -0.70
     locality
    -0.70
    mitter
    -0.69
    rero
    -0.69
     exha
    -0.68
    POSITIVE LOGITS
    88
    1.01
    00
    0.99
    32
    0.98
    76
    0.98
    80
    0.98
    765
    0.98
    86
    0.96
    808
    0.92
    79
    0.91
    325
    0.90
    Activations Density 0.040%

    No Known Activations