© 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. 7-RES-JB
    11. 13056
    Prev
    Next
    INDEX
    Explanations

    phrases indicating emphasis or importance

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "that's what."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    robe
    -0.76
    eer
    -0.66
    ji
    -0.64
    fw
    -0.63
    ardless
    -0.62
    uttering
    -0.62
    ãĥ¼ãĥ³
    -0.61
    still
    -0.61
    hips
    -0.61
    UNE
    -0.60
    POSITIVE LOGITS
     happens
    1.18
     happened
    1.13
    soever
    1.03
     happ
    0.92
     separates
    0.89
    xual
    0.85
     Happ
    0.84
     transpired
    0.82
     distinguishes
    0.78
     happen
    0.75
    Activations Density 0.046%

    No Known Activations