© 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. 0-RES-JB
    11. 6761
    Prev
    Next
    INDEX
    Explanations

    dates and numbers in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numeric values, particularly those formatted as codes or identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     three
    -0.71
     five
    -0.71
     prep
    -0.70
     tens
    -0.67
     four
    -0.67
     six
    -0.65
     120
    -0.64
     90
    -0.64
     110
    -0.63
     culture
    -0.63
    POSITIVE LOGITS
    28
    2.81
    27
    2.67
    29
    2.62
    26
    2.50
    23
    2.25
    22
    2.22
    25
    2.22
    24
    2.20
    21
    2.17
    35
    2.12
    Activations Density 0.053%

    No Known Activations