© 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. 2-RES-JB
    11. 12928
    Prev
    Next
    INDEX
    Explanations

    mentions of awards, nominations, and achievements in various fields such as acting and filmmaking

    oai_token-act-pair · gpt-3.5-turbo

    elements related to film nominations and performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    insured
    -0.72
     governed
    -0.66
     subsistence
    -0.66
     administr
    -0.65
    hower
    -0.65
     actu
    -0.64
    igent
    -0.64
    abus
    -0.61
    afety
    -0.59
    seless
    -0.58
    POSITIVE LOGITS
     cinematic
    0.94
     soundtrack
    0.84
     sitcom
    0.76
     comedic
    0.75
     Cartoon
    0.74
     genre
    0.73
    Writer
    0.72
     premie
    0.71
    Movie
    0.71
     cinem
    0.71
    Activations Density 3.601%

    No Known Activations