© 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. 1-RES-JB
    11. 24175
    Prev
    Next
    INDEX
    Explanations

    the word "choke" or variations of it related to physical restraint or suffocation

    oai_token-act-pair · gpt-3.5-turbo

    terms related to choking, including both the action and its consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CTV
    -0.74
    elf
    -0.70
    ocent
    -0.69
    arians
    -0.68
    udeb
    -0.67
    debian
    -0.67
    igation
    -0.67
    Tu
    -0.66
    JP
    -0.65
    iances
    -0.65
    POSITIVE LOGITS
     choke
    1.20
     choking
    1.03
     choked
    0.99
    leneck
    0.90
     throat
    0.83
     hog
    0.76
    weed
    0.72
    NetMessage
    0.71
     proble
    0.71
    pipe
    0.71
    Activations Density 0.006%

    No Known Activations