© 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. 20842
    Prev
    Next
    INDEX
    Explanations

    mentions of touch-related technologies or features

    oai_token-act-pair · gpt-3.5-turbo

    references to touch technology and related sensors

    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
    ais
    -0.77
    swick
    -0.76
     [|
    -0.75
    èĢ
    -0.70
    adiator
    -0.70
    åŃ
    -0.67
     Clown
    -0.66
    ormal
    -0.66
    committee
    -0.65
    DEF
    -0.65
    POSITIVE LOGITS
     touch
    0.98
    stones
    0.96
    stone
    0.92
    touch
    0.86
    Arcade
    0.83
    downs
    0.82
    ables
    0.81
    pad
    0.80
    backs
    0.76
     fingertips
    0.75
    Activations Density 0.011%

    No Known Activations