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

    Neuronpedia

    Jacobian LensNEW
    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. 7882
    Prev
    Next
    INDEX
    Explanations

    negatively connotated words or phrases, particularly related to mistakes or misdeeds

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of mistakes or errors

    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
    ulhu
    -0.71
    minster
    -0.68
     Fres
    -0.67
     Collider
    -0.62
     cooled
    -0.62
    gel
    -0.62
    Lago
    -0.61
    Fra
    -0.60
    retty
    -0.59
    raltar
    -0.58
    POSITIVE LOGITS
    vous
    0.90
    ukong
    0.76
    dule
    0.76
    gotten
    0.75
    ammad
    0.70
    ceived
    0.70
    WARE
    0.70
    rued
    0.68
    Ö
    0.67
    adows
    0.67
    Activations Density 0.050%

    No Known Activations