© 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. 10-RES-JB
    11. 23511
    Prev
    Next
    INDEX
    Explanations

    places or entities that are present or involved in every possible scenario

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to various entities and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iths
    -0.67
     Relations
    -0.65
     Abilities
    -0.63
     Clouds
    -0.62
    comings
    -0.62
    Loading
    -0.62
     reservoirs
    -0.61
     metaphors
    -0.60
    stals
    -0.60
     Horses
    -0.59
    POSITIVE LOGITS
     imaginable
    1.85
     conceivable
    1.24
     except
    1.11
     individually
    0.94
    except
    0.86
    soever
    0.83
     ounce
    0.82
     ever
    0.78
     irrespective
    0.78
    bender
    0.75
    Activations Density 0.163%

    No Known Activations