© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 21822
    Prev
    Next
    INDEX
    Explanations

    hyphenated phrases indicating a broad or open range or area

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a wide range or variety

    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
     Phi
    -0.77
     signs
    -0.72
     Soda
    -0.71
     Tycoon
    -0.66
     doctor
    -0.66
     awhile
    -0.63
     starters
    -0.63
     Scrib
    -0.63
     ingred
    -0.63
     Reed
    -0.62
    POSITIVE LOGITS
    ranging
    1.64
    reaching
    1.47
    spread
    1.31
    eyed
    1.29
    range
    1.29
    ranged
    1.28
    quartered
    1.21
    scale
    1.18
    bodied
    1.14
    spect
    1.12
    Activations Density 0.030%

    No Known Activations