© 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. 8-RES-JB
    11. 17612
    Prev
    Next
    INDEX
    Explanations

    phrases where the word "well" is used in a particular context

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the word "well"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -0.82
    lete
    -0.76
    psons
    -0.75
    ict
    -0.75
    atform
    -0.73
    icka
    -0.72
    Claim
    -0.72
    Äĩ
    -0.71
    ircraft
    -0.71
    venants
    -0.71
    POSITIVE LOGITS
     uh
    1.07
     yeah
    0.86
     crap
    0.83
     blah
    0.82
    whatever
    0.79
    fuck
    0.79
     ______
    0.76
     shit
    0.76
    yeah
    0.76
     dunno
    0.76
    Activations Density 0.097%

    No Known Activations