© 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. 10-RES-JB
    11. 20382
    Prev
    Next
    INDEX
    Explanations

    prepositions 'in' and 'around' followed by a location

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" in various contexts

    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
    oulos
    -0.67
     Blow
    -0.66
     caution
    -0.60
     Fasc
    -0.59
     Consent
    -0.59
     Fool
    -0.54
     Appeal
    -0.54
    heed
    -0.54
     Lemon
    -0.53
     Sheep
    -0.53
    POSITIVE LOGITS
     around
    1.17
    near
    1.00
    around
    0.95
    rogen
    0.90
     outside
    0.87
     beyond
    0.86
    rogens
    0.85
    rology
    0.84
     surrounding
    0.84
     vicinity
    0.83
    Activations Density 0.023%

    No Known Activations