© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 24079
    Prev
    Next
    INDEX
    Explanations

    personal opinions or statements made by the first person

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions and statements

    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
    senal
    -0.67
    ommel
    -0.66
    cribed
    -0.62
    è¦ļéĨĴ
    -0.62
    naire
    -0.61
    urated
    -0.58
    sbm
    -0.58
    achus
    -0.54
    esc
    -0.54
    elle
    -0.53
    POSITIVE LOGITS
     nonetheless
    1.31
     nevertheless
    1.26
     ALSO
    1.21
     also
    1.16
     still
    1.02
     dig
    0.97
    etheless
    0.96
     gotta
    0.88
    also
    0.87
     NEVER
    0.86
    Activations Density 0.252%

    No Known Activations