© 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. 21536
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers and symbols following a specific pattern

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers, specifically focusing on their frequency and combinations

    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
    034
    -0.74
    909
    -0.73
     Gutenberg
    -0.69
    ãĥķãĤ©
    -0.69
    iqu
    -0.66
    vier
    -0.65
    035
    -0.64
    onics
    -0.64
    032
    -0.63
    036
    -0.63
    POSITIVE LOGITS
     externalToEVAOnly
    0.71
     wart
    0.67
     Kore
    0.65
     partName
    0.63
    ा
    0.62
    âĢ²
    0.62
     ILCS
    0.61
     ANN
    0.59
    mAh
    0.57
     Sabha
    0.57
    Activations Density 0.118%

    No Known Activations