© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 14717
    Prev
    Next
    INDEX
    Explanations

    references to things being evaluated or judged

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve the concept of being "considered" or judged in some manner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ring
    -0.69
     Alley
    -0.67
    "}
    -0.65
    owl
    -0.64
    driver
    -0.63
     Racer
    -0.63
    inas
    -0.62
    cart
    -0.61
    arling
    -0.60
     Planes
    -0.60
    POSITIVE LOGITS
    phas
    0.90
    ilitarian
    0.82
     favorably
    0.81
     considered
    0.80
    iotics
    0.75
     Tradable
    0.73
    onyms
    0.73
     consider
    0.72
     aloud
    0.72
     MFT
    0.70
    Activations Density 0.019%

    No Known Activations