© 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. 12134
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or behaviors carried out by people

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating actions or experiences related to decision-making or public sentiment

    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
    Ü
    -0.60
     Everything
    -0.60
     Roundup
    -0.60
     Adventures
    -0.60
     Quarter
    -0.59
    ãĤ´
    -0.59
     Athletics
    -0.59
     Buster
    -0.59
     sorts
    -0.58
     Guys
    -0.58
    POSITIVE LOGITS
    Reviewed
    0.73
    nai
    0.71
    rake
    0.70
    ometric
    0.68
    iw
    0.67
    wolves
    0.67
    horn
    0.66
     outright
    0.66
    seys
    0.66
    pees
    0.66
    Activations Density 0.227%

    No Known Activations