© 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. 1-RES-JB
    11. 3956
    Prev
    Next
    INDEX
    Explanations

    incomplete phrases leading to suggestions or prompts for website forms or registration processes

    oai_token-act-pair · gpt-3.5-turbo

    terminology related to gaming or powers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    士
    -0.74
    unker
    -0.73
    vation
    -0.70
    ÑĢ
    -0.70
    hess
    -0.70
    ources
    -0.70
    anus
    -0.69
     sacrific
    -0.69
     destro
    -0.68
    ãĥ¼ãĥ³
    -0.68
    POSITIVE LOGITS
     Banking
    0.70
     Morse
    0.69
     Finger
    0.67
     Reno
    0.66
    SW
    0.64
     Mint
    0.64
    Scope
    0.63
    Natural
    0.63
    AAA
    0.63
     Atomic
    0.62
    Activations Density 0.000%

    No Known Activations