© 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. 3021
    Prev
    Next
    INDEX
    Explanations

    adjectives followed by a noun

    oai_token-act-pair · gpt-3.5-turbo

    keywords associated with complexity and ambiguity in situations

    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
    itta
    -0.62
    wow
    -0.61
    urai
    -0.61
    hatt
    -0.60
    anwhile
    -0.59
    illi
    -0.56
    isin
    -0.56
    DERR
    -0.55
    watching
    -0.55
    oward
    -0.55
    POSITIVE LOGITS
     ones
    2.33
     hers
    1.46
     ours
    1.41
     theirs
    1.40
     one
    1.37
     yours
    1.34
     Ones
    1.14
     mine
    1.03
    one
    0.93
     ONE
    0.86
    Activations Density 0.596%

    No Known Activations