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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 17107
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically related to individuals or companies

    oai_token-act-pair · gpt-3.5-turbo

    individual letters, particularly those appearing frequently in names and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.79
    omaly
    -0.70
     anonymity
    -0.65
     hostages
    -0.63
     wrath
    -0.63
    Ĥİ
    -0.62
    ĺħ
    -0.62
     privacy
    -0.60
    ģ«
    -0.60
     plutonium
    -0.60
    POSITIVE LOGITS
    inki
    0.80
    akeru
    0.79
    achus
    0.75
    learning
    0.72
    vec
    0.71
    oys
    0.71
    eret
    0.70
    Tal
    0.69
    initialized
    0.69
    oku
    0.69
    Activations Density 0.082%

    No Known Activations