© 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. 9347
    Prev
    Next
    INDEX
    Explanations

    words related to sequels and continuations in various contexts, such as movies or books

    oai_token-act-pair · gpt-3.5-turbo

    references to sequels and related films

    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
     Applicant
    -0.65
     Column
    -0.65
    auna
    -0.62
    Statistics
    -0.62
    verning
    -0.61
    ickr
    -0.60
    ¬¼
    -0.60
    maxwell
    -0.59
    ande
    -0.59
     econom
    -0.59
    POSITIVE LOGITS
     adaptation
    1.37
     sequel
    1.26
     starring
    1.21
     sequels
    1.19
     trilogy
    1.13
     reboot
    1.10
    quel
    1.08
     adaptations
    1.08
     installment
    1.06
     Deadpool
    1.04
    Activations Density 0.272%

    No Known Activations