© 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. 6-RES-JB
    11. 15425
    Prev
    Next
    INDEX
    Explanations

    references to physical ropes, wires, or similar objects

    oai_token-act-pair · gpt-3.5-turbo

    references to ropes and related equipment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ropolitan
    -0.91
    ctuary
    -0.88
    ãĥ´
    -0.81
    apolis
    -0.78
    esson
    -0.76
    hem
    -0.75
    ãĥĨãĤ£
    -0.74
    ansion
    -0.73
    insula
    -0.72
    itia
    -0.71
    POSITIVE LOGITS
     rope
    1.00
     bondage
    0.97
     strap
    0.89
     ropes
    0.83
     Grip
    0.82
    asso
    0.81
     climbs
    0.80
     ladder
    0.79
     climbing
    0.78
     snakes
    0.76
    Activations Density 0.029%

    No Known Activations