© 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. 6746
    Prev
    Next
    INDEX
    Explanations

    numbers and trigger words related to competitive activities or events

    oai_token-act-pair · gpt-3.5-turbo

    numerical values and their related context in various forms

    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
    ©¶æ¥µ
    -0.95
     Hyder
    -0.81
    ãĥ´ãĤ¡
    -0.76
    hern
    -0.75
    çIJ
    -0.73
     Parables
    -0.72
    olitan
    -0.72
     mund
    -0.71
    Els
    -0.71
    sever
    -0.71
    POSITIVE LOGITS
     kill
    1.12
     bake
    1.07
     call
    1.05
     shoot
    1.04
     burn
    1.04
     catch
    1.04
     sell
    1.03
     vote
    1.03
     throw
    1.03
     ride
    1.03
    Activations Density 0.269%

    No Known Activations