© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 14468
    Prev
    Next
    INDEX
    Explanations

    abbreviations and acronyms

    oai_token-act-pair · gpt-3.5-turbo

    titles of high-grossing movies along with their earnings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respectively
    -0.56
    ]."
    -0.49
     indistinguishable
    -0.48
    $$$$
    -0.46
     theirs
    -0.45
    chuk
    -0.45
    }.
    -0.45
    $.
    -0.45
    onto
    -0.44
     hers
    -0.44
    POSITIVE LOGITS
     largeDownload
    0.61
    ccording
    0.55
     partName
    0.55
     QUEST
    0.52
    terness
    0.51
     FANTASY
    0.51
    enhagen
    0.51
     FILE
    0.48
    utions
    0.47
     DRAGON
    0.46
    Activations Density 6.681%

    No Known Activations