© 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. 22645
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to politics or organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Fine" in various contexts, as well as related terms indicating quality

    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
    PsyNetMessage
    -0.89
    raltar
    -0.87
    sworth
    -0.80
    omnia
    -0.74
    hip
    -0.74
     Kut
    -0.74
    jri
    -0.73
    soDeliveryDate
    -0.73
     Metatron
    -0.72
    è¦ļéĨĴ
    -0.69
    POSITIVE LOGITS
     Gael
    1.13
     Fine
    1.01
    Fine
    0.98
    fine
    0.96
     tuning
    0.86
     fine
    0.84
    «ĺ
    0.74
     Tune
    0.74
     arts
    0.68
     Arts
    0.67
    Activations Density 0.009%

    No Known Activations