© 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. 8-RES-JB
    11. 1803
    Prev
    Next
    INDEX
    Explanations

    years related to future predictions or targets

    oai_token-act-pair · gpt-3.5-turbo

    references to specific future years and dates related to projections or targets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iqu
    -0.83
    kell
    -0.76
    ographed
    -0.69
    iera
    -0.67
    76561
    -0.66
    abilia
    -0.66
    hedral
    -0.66
    este
    -0.64
    afort
    -0.64
    quart
    -0.63
    POSITIVE LOGITS
     onwards
    0.99
     onward
    0.89
     2021
    0.85
     timeframe
    0.85
     census
    0.83
     2020
    0.78
     ILCS
    0.76
    2020
    0.76
    ãĥ¼ãĥ«
    0.75
    âĢķ
    0.74
    Activations Density 0.036%

    No Known Activations