© 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. 12842
    Prev
    Next
    INDEX
    Explanations

    differing accounts or descriptions of situations or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to varying accounts or interpretations of situations

    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
    efficiency
    -0.62
    arton
    -0.59
     deadliest
    -0.58
    indu
    -0.58
    nee
    -0.57
     Led
    -0.57
    NOT
    -0.57
    cluded
    -0.56
    moon
    -0.56
     Investigative
    -0.56
    POSITIVE LOGITS
     differing
    0.98
     depending
    0.97
     configurations
    0.93
     sexes
    0.89
     different
    0.88
    paces
    0.87
    agos
    0.84
     imaginable
    0.83
     varying
    0.82
     styles
    0.82
    Activations Density 0.245%

    No Known Activations