© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 7362
    Prev
    Next
    INDEX
    Explanations

    words related to differences or variations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter 's' in various contexts

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

    No Comments

    Negative Logits
     Pwr
    -0.42
     Nutrition
    -0.36
    Ĥª
    -0.35
     Shot
    -0.32
     Klingon
    -0.32
     Prim
    -0.32
     hunter
    -0.31
     Info
    -0.29
     racket
    -0.29
     Nero
    -0.28
    POSITIVE LOGITS
    nown
    0.48
    ust
    0.44
    theless
    0.42
    yond
    0.42
    actly
    0.40
    gins
    0.40
    oyal
    0.40
    omew
    0.39
    ould
    0.38
    ailable
    0.38
    Activations Density 1.029%

    No Known Activations