© 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. 4-RES-JB
    11. 14913
    Prev
    Next
    INDEX
    Explanations

    mathematical operations, specifically multiplication and division

    oai_token-act-pair · gpt-3.5-turbo

    mathematical operations and references related to multiplication

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

    No Comments

    Negative Logits
    oho
    -0.74
    bones
    -0.70
    hoff
    -0.69
    cknowled
    -0.69
    walker
    -0.68
     Pirate
    -0.67
    hov
    -0.67
    76561
    -0.66
    ãģł
    -0.65
    twitch
    -0.65
    POSITIVE LOGITS
    ithmetic
    0.92
     multiply
    0.90
     increment
    0.90
     multiplication
    0.89
    ulative
    0.89
     fractions
    0.87
    umbers
    0.84
    multipl
    0.83
     additive
    0.83
     numer
    0.82
    Activations Density 0.036%

    No Known Activations