© 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. 18389
    Prev
    Next
    INDEX
    Explanations

    adjectives describing emotions or qualities

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinion or evaluations

    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
    rontal
    -0.67
     hemor
    -0.67
     coli
    -0.64
     downed
    -0.63
    mop
    -0.63
     boarded
    -0.62
    eties
    -0.60
    mercial
    -0.59
    raph
    -0.58
    ideon
    -0.57
    POSITIVE LOGITS
    SPONSORED
    0.86
    ?:
    0.83
     varies
    0.79
     differs
    0.78
     distinguishes
    0.72
     illustrates
    0.70
    Story
    0.67
     differed
    0.66
    requires
    0.66
     boils
    0.66
    Activations Density 0.286%

    No Known Activations