© 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. 7336
    Prev
    Next
    INDEX
    Explanations

    phrases related to lists or articles with various topics being mentioned

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks or formatting cues in the text

    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
     deceived
    -0.76
     dissu
    -0.74
     afar
    -0.73
     indifferent
    -0.73
    utic
    -0.71
     estranged
    -0.69
     innocence
    -0.69
     obliter
    -0.69
    uca
    -0.69
     unwilling
    -0.69
    POSITIVE LOGITS
    Discussion
    1.17
    Summary
    1.07
    Disclaimer
    1.04
    Guest
    1.03
    rawdownloadcloneembedreportprint
    1.03
    Pages
    0.99
    Introduction
    0.98
    Examples
    0.98
    Details
    0.97
    Anyway
    0.96
    Activations Density 0.738%

    No Known Activations