© 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. 0-RES-JB
    11. 22350
    Prev
    Next
    INDEX
    Explanations

    mentions of temporary periods of time or assignments

    oai_token-act-pair · gpt-3.5-turbo

    references to fixed periods of time spent in a specific role or activity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    raq
    -0.65
    hen
    -0.65
     Resolution
    -0.64
    matic
    -0.62
    ported
    -0.62
    iru
    -0.61
    ase
    -0.61
    iana
    -0.59
    Anonymous
    -0.58
     Thomson
    -0.57
    POSITIVE LOGITS
     stint
    3.65
     tenure
    1.17
     gigs
    1.05
     foray
    1.02
     bouts
    1.02
     cameo
    1.01
     periods
    1.00
     outings
    1.00
     internship
    0.94
     resid
    0.93
    Activations Density 0.009%

    No Known Activations