© 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. 6-RES-JB
    11. 20635
    Prev
    Next
    INDEX
    Explanations

    adjectives and adverbs with emphasis or intensity, as well as structured noun phrases indicating specific characteristics

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and descriptors indicating levels of quality or intensity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Papers
    -0.65
     Uriel
    -0.62
    amaz
    -0.61
    wat
    -0.56
     :=
    -0.54
    missing
    -0.54
     Dmitry
    -0.54
     dstg
    -0.53
     Mulcair
    -0.53
    atography
    -0.52
    POSITIVE LOGITS
     confines
    0.84
     orbit
    0.81
     pasture
    0.81
     predetermined
    0.79
     ausp
    0.75
     hosp
    0.73
     vantage
    0.72
     standpoint
    0.70
     plantation
    0.69
     disadvantage
    0.69
    Activations Density 0.782%

    No Known Activations