© 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. 10-RES-JB
    11. 8546
    Prev
    Next
    INDEX
    Explanations

    adverbs or adjectives indicating the degree of a quality or action

    oai_token-act-pair · gpt-3.5-turbo

    expressions of value judgment and comparisons of good and bad

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahime
    -0.86
    anches
    -0.78
     Parsons
    -0.77
    ulkan
    -0.77
     Petersen
    -0.76
     Parade
    -0.75
    ipel
    -0.74
    incarn
    -0.74
    eph
    -0.74
     Sylvia
    -0.73
    POSITIVE LOGITS
     bad
    1.59
     good
    1.56
     GOOD
    1.51
     BAD
    1.42
    good
    1.37
    bad
    1.36
     evil
    1.32
     crappy
    1.30
     Good
    1.29
     lousy
    1.28
    Activations Density 0.320%

    No Known Activations