© 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. 22806
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal actions and petitions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to" 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
     Laksh
    -0.73
     vib
    -0.69
     Passion
    -0.66
    furt
    -0.64
     coping
    -0.62
     borne
    -0.62
     tending
    -0.62
     Problem
    -0.61
    problem
    -0.61
     footprints
    -0.59
    POSITIVE LOGITS
     postpone
    1.11
     revoke
    1.09
     abolish
    1.08
     rename
    1.07
     reopen
    1.04
     remove
    1.03
     exclude
    1.02
     oust
    1.00
     compel
    1.00
     clarify
    0.98
    Activations Density 0.129%

    No Known Activations