© 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. 1-RES-JB
    11. 10225
    Prev
    Next
    INDEX
    Explanations

    positive affirmations or strong endorsements

    oai_token-act-pair · gpt-3.5-turbo

    words related to strong positive responses or approvals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nan
    -0.69
    bil
    -0.68
    perature
    -0.65
    士
    -0.65
    nesota
    -0.65
     skelet
    -0.65
     procure
    -0.63
    othy
    -0.63
    ORT
    -0.61
    pool
    -0.60
    POSITIVE LOGITS
    ounded
    1.15
    ounding
    1.10
    oslav
    0.92
    ounds
    0.91
    OUND
    0.84
    onent
    0.79
    soType
    0.79
     Sadd
    0.78
    ogle
    0.70
    SourceFile
    0.69
    Activations Density 0.009%

    No Known Activations