© 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. 6-RES-JB
    11. 17197
    Prev
    Next
    INDEX
    Explanations

    names of people or possibly locations

    oai_token-act-pair · gpt-3.5-turbo

    references to votes, elections, or polling data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deterrent
    -0.58
    Compat
    -0.54
     GOODMAN
    -0.53
     guiActiveUnfocused
    -0.53
     deterrence
    -0.53
     attRot
    -0.53
    metics
    -0.52
    ".[
    -0.52
    ģ«
    -0.50
    ?".
    -0.50
    POSITIVE LOGITS
    reprene
    0.62
    itone
    0.59
    ragon
    0.57
     himself
    0.55
    çĶ°
    0.55
     Himself
    0.54
    ãĥīãĥ©ãĤ´ãĥ³
    0.54
     pseudonym
    0.53
    cephal
    0.52
    selage
    0.51
    Activations Density 1.620%

    No Known Activations