© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 3317
    Prev
    Next
    INDEX
    Explanations

    descriptions of expectation or speculation

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating hypothetical situations or expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cance
    -0.70
    usha
    -0.69
    updated
    -0.67
    clips
    -0.61
     XT
    -0.61
     Scand
    -0.60
    side
    -0.60
     Cutting
    -0.60
    vier
    -0.59
    sei
    -0.59
    POSITIVE LOGITS
     normally
    0.98
     characterize
    0.92
     expect
    0.91
     ordinarily
    0.88
     perceive
    0.86
     deem
    0.83
     otherwise
    0.83
    ²¾
    0.78
     encounter
    0.78
    »Ĵ
    0.76
    Activations Density 0.120%

    No Known Activations