© 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. 6274
    Prev
    Next
    INDEX
    Explanations

    opinions expressed in text

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions or judgments

    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
    perty
    -0.73
     Stuff
    -0.69
     Yourself
    -0.61
    ette
    -0.60
    ufact
    -0.60
     Creature
    -0.60
     Written
    -0.59
    vez
    -0.57
    arsity
    -0.57
     Secrets
    -0.56
    POSITIVE LOGITS
    phas
    0.72
     anyways
    0.66
     anyway
    0.65
    é¾įåĸļ士
    0.63
     terminating
    0.61
     unres
    0.59
     euth
    0.59
     boils
    0.58
    iewicz
    0.58
    âĶĢâĶĢâĶĢâĶĢ
    0.57
    Activations Density 0.060%

    No Known Activations