© 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. 9-RES-JB
    11. 15575
    Prev
    Next
    INDEX
    Explanations

    origin-related terms or concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "origin" and its various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.75
    eneg
    -0.70
    ĵĺ
    -0.69
     helicop
    -0.68
     toget
    -0.65
    channelAvailability
    -0.64
    isSpecialOrderable
    -0.63
    orld
    -0.61
    anyahu
    -0.61
    scl
    -0.60
    POSITIVE LOGITS
    ator
    1.28
    ators
    1.24
    ates
    1.11
    uating
    0.84
    ual
    0.82
    uation
    0.79
    ating
    0.78
    uated
    0.76
    itious
    0.76
    waters
    0.75
    Activations Density 0.044%

    No Known Activations