© 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. 245
    Prev
    Next
    INDEX
    Explanations

    words related to being on the verge of something happening

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating readiness or anticipation of future events

    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
    cause
    -0.62
    amba
    -0.61
    bey
    -0.60
    friend
    -0.60
    jay
    -0.60
     CLSID
    -0.59
    Footnote
    -0.59
    GS
    -0.58
    tein
    -0.58
    sam
    -0.58
    POSITIVE LOGITS
    abouts
    0.83
    ebus
    0.77
    rons
    0.76
    olicy
    0.75
     unbeliev
    0.73
    etsk
    0.72
    cture
    0.71
    eous
    0.71
    edIn
    0.70
     poised
    0.70
    Activations Density 0.010%

    No Known Activations