© 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. 7-RES-JB
    11. 3104
    Prev
    Next
    INDEX
    Explanations

    instances of the word "still" in various contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    origin
    -0.73
    ighth
    -0.70
    ocol
    -0.66
    vals
    -0.64
    yond
    -0.63
    ISE
    -0.63
    imer
    -0.63
    rosso
    -0.62
    illet
    -0.62
    benef
    -0.62
    POSITIVE LOGITS
     pacing
    0.91
     staring
    0.85
     amid
    0.77
     amidst
    0.77
     screaming
    0.76
     asleep
    0.75
    enance
    0.75
     chanting
    0.73
     yelling
    0.73
     helpless
    0.73
    Activations Density 0.216%

    No Known Activations