© 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. 6-RES-JB
    11. 19640
    Prev
    Next
    INDEX
    Explanations

    scientists and researchers, potentially led by specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of professionals or experts involved in research or scientific endeavors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shed
    -0.66
     Spartan
    -0.63
     Bless
    -0.63
     Clause
    -0.62
    ãĤ¨ãĥ«
    -0.60
     Rampage
    -0.60
     Slave
    -0.59
     Alive
    -0.59
     Sidd
    -0.58
     quarry
    -0.58
    POSITIVE LOGITS
     converge
    0.92
     conver
    0.82
    uits
    0.81
     relating
    0.80
     comprising
    0.77
    hooting
    0.74
     vying
    0.73
     including
    0.72
    votes
    0.70
     spanning
    0.69
    Activations Density 0.328%

    No Known Activations