© 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. 19676
    Prev
    Next
    INDEX
    Explanations

    phrases or proper nouns that have significance or importance

    oai_token-act-pair · gpt-3.5-turbo

    important nouns and phrases related to identity and general topics or subjects in a discussion

    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
     cones
    -0.68
     Thomson
    -0.62
     Rue
    -0.58
     PACs
    -0.55
     sockets
    -0.55
     journals
    -0.54
     @@
    -0.54
     JM
    -0.53
     clusters
    -0.53
     Grail
    -0.52
    POSITIVE LOGITS
    esthetic
    0.81
    onian
    0.72
    ometric
    0.68
    kie
    0.65
    ño
    0.62
    usal
    0.62
    orph
    0.59
    owski
    0.59
    own
    0.59
    ggles
    0.58
    Activations Density 1.172%

    No Known Activations