© 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. 10-RES-JB
    11. 11113
    Prev
    Next
    INDEX
    Explanations

    mentions of specific timeframes, such as "three years," "six months," "two weeks," and "ten years."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future timeframes or durations

    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
     incent
    -0.72
    antam
    -0.68
    inse
    -0.68
    inite
    -0.65
    wards
    -0.64
    reon
    -0.64
    uer
    -0.63
     comr
    -0.61
    insula
    -0.61
    enberg
    -0.60
    POSITIVE LOGITS
     span
    1.07
     increments
    0.92
    '
    0.82
     ago
    0.74
    !'
    0.74
    hops
    0.72
     time
    0.71
     timeframe
    0.71
    '.
    0.69
     intervals
    0.67
    Activations Density 0.088%

    No Known Activations