© 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. 6824
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something that is expected or anticipated to happen in the future

    oai_token-act-pair · gpt-3.5-turbo

    phrases beginning with "has yet to" indicating unfinished actions or statements

    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
     Rite
    -0.77
     Polo
    -0.73
     Advertisement
    -0.69
    Firstly
    -0.68
     Gateway
    -0.68
    SourceFile
    -0.67
     Novel
    -0.67
    quickShipAvailable
    -0.67
    Nap
    -0.67
    Policy
    -0.65
    POSITIVE LOGITS
     sustain
    0.91
     confirm
    0.84
    pleting
    0.83
     complete
    0.82
     fulfill
    0.82
     settle
    0.82
     faint
    0.81
     satisfy
    0.81
    pletion
    0.80
     disappoint
    0.79
    Activations Density 0.045%

    No Known Activations