© 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. 3-RES-JB
    11. 5000
    Prev
    Next
    INDEX
    Explanations

    locations or settings described as significant, notable, or special

    oai_token-act-pair · gpt-3.5-turbo

    references to significant locations or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rd
    -0.72
    vous
    -0.67
    TAG
    -0.66
     UCHIJ
    -0.63
    agascar
    -0.62
    FIN
    -0.62
    iscal
    -0.61
     Rudd
    -0.60
    azel
    -0.60
     Latest
    -0.60
    POSITIVE LOGITS
    bos
    1.11
    holders
    0.98
    holder
    0.93
    ername
    0.78
    places
    0.77
    upon
    0.75
    Place
    0.70
    down
    0.70
     place
    0.67
     Temperature
    0.67
    Activations Density 0.037%

    No Known Activations