© 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. 11-RES-JB
    11. 9900
    Prev
    Next
    INDEX
    Explanations

    words related to events or actions linked to specific dates or schedules

    oai_token-act-pair · gpt-3.5-turbo

    references to events and experiences over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oppers
    -0.68
    units
    -0.67
    aware
    -0.63
    Tags
    -0.63
    İĭ
    -0.62
     arsen
    -0.61
    facts
    -0.60
    etooth
    -0.59
     currents
    -0.59
    inguishable
    -0.59
    POSITIVE LOGITS
     audition
    1.33
     interview
    1.25
     rehearsal
    1.19
     trip
    1.17
     outing
    1.17
     rematch
    1.14
     shoot
    1.13
     match
    1.11
     tour
    1.10
     workout
    1.10
    Activations Density 0.435%

    No Known Activations