© 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. 4-RES-JB
    11. 14771
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of transferring something from one person to another

    oai_token-act-pair · gpt-3.5-turbo

    instances 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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tonight
    -0.74
    urity
    -0.68
    vell
    -0.68
    00000
    -0.66
    00200000
    -0.66
    AIR
    -0.66
    Tonight
    -0.66
    9999
    -0.66
    ITAL
    -0.65
    amins
    -0.64
    POSITIVE LOGITS
    shake
    0.91
     handed
    0.87
    maid
    0.85
    ily
    0.83
    handed
    0.81
    picked
    0.79
    awed
    0.77
    washing
    0.73
    otom
    0.72
    wheel
    0.71
    Activations Density 0.013%

    No Known Activations