© 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. 11-RES-JB
    11. 10282
    Prev
    Next
    INDEX
    Explanations

    phrases indicating high degree of appreciation or enjoyment

    oai_token-act-pair · gpt-3.5-turbo

    infinitive verbs, particularly those indicating actions or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arity
    -0.77
    vich
    -0.74
    urance
    -0.74
    mentioned
    -0.69
    afety
    -0.68
    aration
    -0.67
    urances
    -0.65
    uli
    -0.65
    ļéĨĴ
    -0.65
    illusion
    -0.63
    POSITIVE LOGITS
     contemplate
    1.28
     behold
    1.26
     watch
    1.07
     begin
    1.03
     navigate
    0.97
     undertake
    0.96
     swallow
    0.96
     operate
    0.92
     consume
    0.92
     endure
    0.91
    Activations Density 0.112%

    No Known Activations