© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10438
    Prev
    Next
    INDEX
    Explanations

    terms indicating authority or control over something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hold" and its variations 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
    endix
    -0.76
    icycle
    -0.67
    clerosis
    -0.65
     deceive
    -0.64
     Daylight
    -0.64
     omission
    -0.63
    ologist
    -0.63
    inx
    -0.62
    osal
    -0.62
    ibel
    -0.61
    POSITIVE LOGITS
    hold
    1.10
    holders
    1.07
    holder
    1.01
    holding
    0.96
     sway
    0.94
     hold
    0.94
    held
    0.85
    erness
    0.85
     accountable
    0.80
     captive
    0.77
    Activations Density 0.034%

    No Known Activations