© 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. 8-RES-JB
    11. 6262
    Prev
    Next
    INDEX
    Explanations

    the word "for" followed by a number indicating a positive association with preparedness or suitability

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating readiness or preparedness for something

    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
    loo
    -0.77
    LM
    -0.75
     Accessed
    -0.71
    deen
    -0.71
    ipple
    -0.70
    Force
    -0.68
    nex
    -0.67
    named
    -0.66
    book
    -0.66
    attach
    -0.65
    POSITIVE LOGITS
     experimentation
    0.95
    geries
    0.85
     testing
    0.81
     optimum
    0.79
     greatness
    0.78
     takeoff
    0.78
     retirement
    0.78
     inclusion
    0.76
     whatever
    0.75
     occupancy
    0.75
    Activations Density 0.113%

    No Known Activations