© 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. 14072
    Prev
    Next
    INDEX
    Explanations

    time-related references and durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases referencing time periods and duration of events

    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
    ansk
    -0.74
     tonight
    -0.71
     tomorrow
    -0.66
     ALWAYS
    -0.64
    estamp
    -0.64
    oris
    -0.63
     torches
    -0.61
     reacts
    -0.61
     awoke
    -0.60
    cdn
    -0.59
    POSITIVE LOGITS
     decade
    1.36
     year
    1.08
     years
    1.08
     fiscal
    1.06
     decades
    0.95
    year
    0.93
     1990
    0.92
     semester
    0.91
     YEAR
    0.87
     summer
    0.82
    Activations Density 0.252%

    No Known Activations