© 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. 9410
    Prev
    Next
    INDEX
    Explanations

    words related to alternative options or courses of action

    oai_token-act-pair · gpt-3.5-turbo

    references to options and alternatives in decision-making contexts

    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
    ĸļ
    -0.86
    ©¶æ¥µ
    -0.76
    PRESS
    -0.76
    Registered
    -0.75
    è£
    -0.72
    phies
    -0.72
    iversary
    -0.69
    asuring
    -0.68
    Ĥİ
    -0.67
    Staff
    -0.67
    POSITIVE LOGITS
     alternatives
    2.06
     options
    2.05
     possibilities
    1.98
     option
    1.70
     possibility
    1.68
     alternative
    1.63
     feasible
    1.54
     viable
    1.52
    Option
    1.52
     Option
    1.46
    Activations Density 0.574%

    No Known Activations