© 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 EvalsExportsinterp-engineNEWAPI 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. 24177
    Prev
    Next
    INDEX
    Explanations

    verbs related to forceful movement or manipulation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to being "dragged" or pulled into situations, often with a negative connotation

    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
    ept
    -0.72
    owler
    -0.67
    ãĥ´ãĤ¡
    -0.66
     Kubrick
    -0.65
    icient
    -0.63
     Tec
    -0.61
    rypted
    -0.60
    tu
    -0.59
    icago
    -0.59
    OTOS
    -0.58
    POSITIVE LOGITS
    glers
    0.78
    gers
    0.77
    azine
    0.73
    ged
    0.73
     broom
    0.71
    along
    0.71
     baggage
    0.71
    ging
    0.70
     ashore
    0.70
    ĸļ
    0.70
    Activations Density 0.043%

    No Known Activations