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

    Neuronpedia

    Jacobian LensNEW
    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. 4831
    Prev
    Next
    INDEX
    Explanations

    idiomatic expressions and phrases known as "offhand" or "offhanded"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to off-duty situations and physical activities

    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
    éĹĺ
    -0.85
    pton
    -0.72
    MAC
    -0.68
    å°Ĩ
    -0.66
    Maria
    -0.65
    ashtra
    -0.63
    apest
    -0.63
    Export
    -0.62
    oother
    -0.61
    emporary
    -0.60
    POSITIVE LOGITS
    fen
    0.71
     shores
    0.65
     territory
    0.64
    atives
    0.64
    planned
    0.62
    productive
    0.61
     Anchorage
    0.60
    ilts
    0.60
     docks
    0.60
    claw
    0.60
    Activations Density 0.108%

    No Known Activations