© 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. 24196
    Prev
    Next
    INDEX
    Explanations

    unusual numerical sequences

    oai_token-act-pair · gpt-3.5-turbo

    numeric representations or references, specifically digits or numerical data

    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
    é¾įå¥ij士
    -0.80
    channelAvailability
    -0.75
    versions
    -0.74
    enture
    -0.72
     EntityItem
    -0.72
    escription
    -0.71
    REDACTED
    -0.69
    dayName
    -0.68
     Lauder
    -0.68
    rill
    -0.68
    POSITIVE LOGITS
    9999
    1.27
    999
    1.23
    06
    1.13
    79
    1.10
    88
    1.10
    08
    1.09
    07
    1.09
    03
    1.08
    04
    1.07
    67
    1.05
    Activations Density 0.031%

    No Known Activations