© 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. 10-RES-JB
    11. 14183
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions involving division and multiplication

    oai_token-act-pair · gpt-3.5-turbo

    mathematical and computational concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    camp
    -0.76
     Jarvis
    -0.74
    odcast
    -0.73
     Walker
    -0.72
     mentor
    -0.68
     Sau
    -0.67
     Breach
    -0.67
    ibur
    -0.66
    Camp
    -0.66
    Hunter
    -0.66
    POSITIVE LOGITS
     decimal
    1.89
     integers
    1.81
     integer
    1.58
     multiplication
    1.51
     digits
    1.48
     arithmetic
    1.44
     exponent
    1.39
     numeric
    1.35
    integer
    1.33
     fractions
    1.32
    Activations Density 0.495%

    No Known Activations