© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 16633
    Prev
    Next
    INDEX
    Explanations

    timestamps in the format of 'a.m.' or 'p.m.' showing the time of day

    oai_token-act-pair · gpt-3.5-turbo

    timestamps and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     discriminating
    -0.62
    igning
    -0.61
     neglig
    -0.60
     harness
    -0.58
     brim
    -0.58
     havens
    -0.58
     totaling
    -0.57
     conduc
    -0.57
     delinquent
    -0.56
     roots
    -0.56
    POSITIVE LOGITS
     EDT
    0.86
    hower
    0.83
     PDT
    0.83
     EST
    0.82
     CST
    0.81
     ET
    0.79
     PST
    0.78
     GMT
    0.73
    seq
    0.72
    mk
    0.68
    Activations Density 0.031%

    No Known Activations