© 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. 7-RES-JB
    11. 17203
    Prev
    Next
    INDEX
    Explanations

    phone numbers and numeric codes

    oai_token-act-pair · gpt-3.5-turbo

    numerical sequences or identifiers, including phone numbers and codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istry
    -0.90
     fencing
    -0.67
     foss
    -0.62
     scenery
    -0.62
    sed
    -0.61
     Tourism
    -0.61
    eral
    -0.59
    igans
    -0.59
     bleeding
    -0.57
     wagon
    -0.57
    POSITIVE LOGITS
    148
    0.91
    120
    0.91
    192
    0.87
    145
    0.86
    134
    0.85
    266
    0.85
    0000000
    0.85
    287
    0.85
    200
    0.85
    157
    0.85
    Activations Density 0.148%

    No Known Activations