© 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. 11-RES-JB
    11. 10231
    Prev
    Next
    INDEX
    Explanations

    arithmetic operations involving numbers and mathematical notation

    oai_token-act-pair · gpt-3.5-turbo

    mathematical operations and numerical relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Role
    -0.72
     playlist
    -0.71
     retrospective
    -0.66
     Coach
    -0.66
     sleeper
    -0.64
     smartest
    -0.61
     tracker
    -0.60
     moratorium
    -0.60
     autop
    -0.60
    visor
    -0.60
    POSITIVE LOGITS
    0000000000000000
    1.39
    ÏĢ
    1.38
    0000000
    1.37
    00000000
    1.33
    +(
    1.30
    000000
    1.27
    ^
    1.22
    9999
    1.21
    /(
    1.19
    147
    1.16
    Activations Density 0.117%

    No Known Activations