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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    11. 8300
    Prev
    Next
    INDEX
    Explanations

    timestamps in GMT (Greenwich Mean Time)

    oai_token-act-pair · gpt-3.5-turbo

    instances of the time zone abbreviation "GMT."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kin
    -0.88
    shared
    -0.81
    benefit
    -0.76
    tons
    -0.75
    par
    -0.73
    ply
    -0.73
    itably
    -0.72
    alcohol
    -0.71
    ãĥ£
    -0.71
    cling
    -0.69
    POSITIVE LOGITS
     GMT
    1.15
    GMT
    0.83
     Mub
    0.79
     CET
    0.77
     Mubarak
    0.74
    UTC
    0.74
     PDT
    0.73
     Seym
    0.73
    EMBER
    0.72
    agascar
    0.71
    Activations Density 0.005%

    No Known Activations