© 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. 548
    Prev
    Next
    INDEX
    Explanations

    mentions of models, both in the context of individuals as well as in the form of representations or examples

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "model" and its variants

    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
    vernment
    -0.86
    usters
    -0.81
    olulu
    -0.80
    ulhu
    -0.77
    kefeller
    -0.71
    azar
    -0.69
    lins
    -0.69
    IELD
    -0.67
    minster
    -0.67
    ttp
    -0.67
    POSITIVE LOGITS
    model
    0.84
    models
    0.79
     Models
    0.76
     photographed
    0.75
     Mayhem
    0.73
     Penal
    0.70
    iste
    0.68
    )=(
    0.66
    urer
    0.65
     Adidas
    0.65
    Activations Density 0.014%

    No Known Activations