© 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. 13317
    Prev
    Next
    INDEX
    Explanations

    references to communication or movement through a specific means or location

    oai_token-act-pair · gpt-3.5-turbo

    references to specific entities, particularly through the use of the word "the."

    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
    bane
    -0.76
    oka
    -0.74
    EMP
    -0.69
     Stamp
    -0.67
    ufact
    -0.66
    tle
    -0.64
    PDATE
    -0.64
    isu
    -0.63
    utherford
    -0.63
    olson
    -0.63
    POSITIVE LOGITS
     channels
    0.90
     labyrinth
    0.89
     prism
    0.88
     intermediary
    0.86
     backdoor
    0.85
     motions
    0.83
     guise
    0.80
     lens
    0.79
     veil
    0.78
     veins
    0.77
    Activations Density 0.164%

    No Known Activations