© 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. 4-RES-JB
    11. 15226
    Prev
    Next
    INDEX
    Explanations

    words related to the process of launching or implementing something, specifically using the term "rollout."

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "rollout" and its associated contexts

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

    No Comments

    Negative Logits
     Sul
    -0.85
    venge
    -0.74
    unin
    -0.74
    resp
    -0.73
    onyms
    -0.73
    uana
    -0.73
    inates
    -0.71
    acts
    -0.70
    inately
    -0.68
    inals
    -0.68
    POSITIVE LOGITS
     rollout
    1.30
    igation
    0.71
     timetable
    0.67
     schedule
    0.67
     backlog
    0.67
    around
    0.66
     delays
    0.66
    tenance
    0.66
     delay
    0.65
     Deploy
    0.65
    Activations Density 0.015%

    No Known Activations