© 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. 1764
    Prev
    Next
    INDEX
    Explanations

    instances where something is being handed over

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "handed" in various contexts

    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
     Tonight
    -0.72
    vell
    -0.71
    issy
    -0.69
    ITAL
    -0.68
    Tonight
    -0.67
    AIR
    -0.67
    âĨij
    -0.66
    00000
    -0.63
    00200000
    -0.63
    alli
    -0.62
    POSITIVE LOGITS
     handed
    0.93
    shake
    0.91
    maid
    0.86
    picked
    0.82
    awed
    0.81
    handed
    0.79
     handing
    0.74
    ily
    0.73
    ragon
    0.73
    hran
    0.73
    Activations Density 0.015%

    No Known Activations