© 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. 3-RES-JB
    11. 11442
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical suspension or pending situations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hanging" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    姫
    -1.00
    ãĤ¡
    -0.88
    ãĥĨãĤ£
    -0.88
    ibel
    -0.84
    utive
    -0.78
     GENERAL
    -0.76
    Merit
    -0.74
    KB
    -0.72
    zyk
    -0.69
    initions
    -0.69
    POSITIVE LOGITS
     hanging
    0.98
     hang
    0.98
    rily
    0.86
     baskets
    0.86
     upside
    0.83
    hang
    0.83
     brill
    0.82
     hung
    0.81
     hanged
    0.78
    wine
    0.77
    Activations Density 0.010%

    No Known Activations