© 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. 9-RES-JB
    11. 16193
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical impact or force

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "knock" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sunrise
    -0.69
    ris
    -0.64
    stice
    -0.64
     RTX
    -0.63
    illery
    -0.63
     Scotia
    -0.62
    mberg
    -0.62
    emale
    -0.62
    rano
    -0.62
    RED
    -0.61
    POSITIVE LOGITS
    down
    1.17
     knock
    0.94
    downs
    0.91
    DOWN
    0.84
     down
    0.83
    outs
    0.82
    ı
    0.82
     unconscious
    0.80
    out
    0.79
    kn
    0.78
    Activations Density 0.040%

    No Known Activations