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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 19753
    Prev
    Next
    INDEX
    Explanations

    mentions of origins or origins of different entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "origin" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    joined
    -0.70
    EMENT
    -0.63
    ucky
    -0.62
    owl
    -0.62
    ĵĺ
    -0.61
    current
    -0.61
    rom
    -0.59
    Agg
    -0.59
    STRUCT
    -0.59
    uster
    -0.59
    POSITIVE LOGITS
     origin
    0.92
    alis
    0.84
    origin
    0.83
    ates
    0.81
     Forge
    0.74
    acy
    0.74
     originate
    0.74
    ator
    0.73
     originating
    0.71
     origins
    0.70
    Activations Density 0.009%

    No Known Activations