© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 7192
    Prev
    Next
    INDEX
    Explanations

    phrases related to theoretical scenarios or hypothetical situations that involve decision-making

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases indicating potential actions or outcomes

    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
     cabinet
    -0.66
     Saying
    -0.65
     Conference
    -0.63
     Neck
    -0.63
     Quart
    -0.63
     citing
    -0.61
    lex
    -0.61
     Martha
    -0.60
     Brass
    -0.59
     Gentleman
    -0.59
    POSITIVE LOGITS
     conflic
    0.86
     characterize
    0.85
     satisfy
    0.84
    accompan
    0.83
     impede
    0.82
     contribute
    0.81
     populate
    0.81
     interfere
    0.77
     culmin
    0.77
     translate
    0.77
    Activations Density 0.139%

    No Known Activations