Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 7645
    Prev
    Next
    INDEX
    Explanations

    references to movies, film directors, and movie-related terms

    oai_token-act-pair · gpt-3.5-turbo

    details about film production and characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     waivers
    -0.71
     clipboard
    -0.66
     Universities
    -0.66
    ESA
    -0.64
     impunity
    -0.63
     Null
    -0.63
     Provision
    -0.63
     unanim
    -0.63
     exemption
    -0.63
     IRC
    -0.62
    POSITIVE LOGITS
     premiered
    1.57
     debuted
    1.34
     depicts
    1.32
     premie
    1.30
     portrays
    1.30
     starring
    1.23
     starred
    1.22
     explores
    1.20
     revolves
    1.17
     narrated
    1.17
    Activations Density 0.241%

    No Known Activations