© 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. 1-RES-JB
    11. 973
    Prev
    Next
    INDEX
    Explanations

    commands related to specific actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of the term "scout" and various negative actions related to dishonesty and bullying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omen
    -0.82
    ammy
    -0.76
    atility
    -0.76
    ighting
    -0.75
    undai
    -0.75
    elaide
    -0.75
    itting
    -0.74
    uilt
    -0.72
    gewater
    -0.70
    omin
    -0.70
    POSITIVE LOGITS
    able
    0.86
    wright
    0.86
    ABLE
    0.86
    crow
    0.85
    vier
    0.78
    buster
    0.77
    craft
    0.76
    WARE
    0.72
    holder
    0.72
    ables
    0.72
    Activations Density 0.051%

    No Known Activations