© 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. 22005
    Prev
    Next
    INDEX
    Explanations

    references to remote activities or control

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "remotely" and related concepts

    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
    ī
    -0.83
    glers
    -0.78
    oria
    -0.76
    hetti
    -0.75
    gio
    -0.73
    ulet
    -0.73
    amins
    -0.71
    erald
    -0.70
    yg
    -0.69
    ifully
    -0.69
    POSITIVE LOGITS
     remotely
    1.04
     pil
    0.88
     detonated
    0.87
    cffffcc
    0.79
     minded
    0.77
     controlled
    0.76
     exting
    0.75
     sensed
    0.73
     armed
    0.71
    ilitary
    0.71
    Activations Density 0.007%

    No Known Activations