© 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. 9-RES-JB
    11. 9011
    Prev
    Next
    INDEX
    Explanations

    time-related expressions, especially those indicating duration

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to duration or the time taken to complete actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.74
    IDA
    -0.67
     Caller
    -0.66
    soType
    -0.66
    Choice
    -0.64
     Continuing
    -0.62
    resy
    -0.62
    ergic
    -0.61
     Danger
    -0.61
    altern
    -0.60
    POSITIVE LOGITS
     realize
    1.31
     realise
    1.22
     reach
    1.16
     achieve
    1.16
     arrive
    1.15
     accomplish
    1.13
     recover
    1.12
     assemble
    1.12
     accumulate
    1.11
     regain
    1.10
    Activations Density 0.116%

    No Known Activations