© 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. 8-RES-JB
    11. 11108
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical actions or procedures

    oai_token-act-pair · gpt-3.5-turbo

    affirmations or strong assertions about individuals or events

    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
    ]),
    -0.65
    inian
    -0.64
     FSA
    -0.61
     âĨij
    -0.61
     Regarding
    -0.59
    anmar
    -0.58
    orial
    -0.57
    rict
    -0.57
     Franch
    -0.56
    uding
    -0.56
    POSITIVE LOGITS
     deserve
    0.74
     deserves
    0.67
    alone
    0.66
     sooner
    0.64
     everywhere
    0.64
    peat
    0.61
    Cause
    0.61
     continues
    0.61
    potion
    0.61
    payers
    0.60
    Activations Density 0.838%

    No Known Activations