© 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. 7040
    Prev
    Next
    INDEX
    Explanations

    mentions of deep, significant, or intense implications, experiences, or changes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "profound" and related phrases signifying significant impact or depth

    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
    ©¶æ
    -0.80
    phis
    -0.69
    paces
    -0.64
    hops
    -0.63
     Garrison
    -0.63
    swick
    -0.63
    rera
    -0.62
    ope
    -0.61
    fight
    -0.61
    matched
    -0.61
    POSITIVE LOGITS
    ly
    0.83
    est
    0.81
     philosophical
    0.75
     impact
    0.72
     implications
    0.71
     significance
    0.70
     profound
    0.70
    ness
    0.70
    itudinal
    0.68
    aughs
    0.67
    Activations Density 0.007%

    No Known Activations