© 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. 17312
    Prev
    Next
    INDEX
    Explanations

    descriptions of situations or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases relating to control and power dynamics

    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
    âĢ
    -0.88
    20439
    -0.87
     âĢ
    -0.87
    \"
    -0.87
    âĹ
    -0.82
    ãĢ
    -0.82
    âĢIJ
    -0.81
    ¨
    -0.80
    .","
    -0.80
    "},"
    -0.80
    POSITIVE LOGITS
     stuff
    1.14
     goddamn
    1.13
     dudes
    1.12
     kinda
    1.11
     weird
    1.08
     pretty
    1.08
     dude
    1.07
     shit
    1.07
     crap
    1.06
     shitty
    1.06
    Activations Density 1.628%

    No Known Activations