© 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. 11-RES-JB
    11. 7042
    Prev
    Next
    INDEX
    Explanations

    references to locations or contexts of being "in"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in" along with references to time or status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uces
    -0.70
    uden
    -0.64
     awoken
    -0.63
    Tickets
    -0.62
    isky
    -0.61
    zsche
    -0.60
     glean
    -0.60
     hoping
    -0.59
    NOW
    -0.59
    enance
    -0.58
    POSITIVE LOGITS
     circulation
    1.27
     existence
    1.24
     operation
    1.09
     possession
    1.01
     use
    1.00
    activated
    0.99
     storage
    0.99
    operative
    0.98
    oper
    0.96
     remission
    0.91
    Activations Density 0.177%

    No Known Activations