© 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. 2965
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a choice between two options

    oai_token-act-pair · gpt-3.5-turbo

    the word "either" and its variations in context

    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
    achus
    -0.83
    appings
    -0.76
    vez
    -0.75
    inav
    -0.74
    biz
    -0.68
    appers
    -0.68
    ussions
    -0.68
    bang
    -0.67
    roxy
    -0.65
    ilit
    -0.64
    POSITIVE LOGITS
    lift
    0.78
    either
    0.73
     overtly
    0.68
     implicitly
    0.63
     halves
    0.63
     Either
    0.63
    Either
    0.62
     willfully
    0.61
     redistributed
    0.61
     side
    0.61
    Activations Density 0.019%

    No Known Activations