© 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. 9527
    Prev
    Next
    INDEX
    Explanations

    terms related to the action of informing or reporting

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "inform."

    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
    âĻ¥
    -0.77
     vain
    -0.73
     Hornets
    -0.71
    KING
    -0.65
    addle
    -0.65
    Water
    -0.64
    iphate
    -0.62
    imposed
    -0.62
    Jordan
    -0.62
    den
    -0.61
    POSITIVE LOGITS
     inform
    1.10
     antioxid
    0.89
    ally
    0.86
    tale
    0.86
    ingly
    0.85
     Subscribe
    0.84
    ially
    0.84
     enqu
    0.80
    ariat
    0.80
     mathemat
    0.79
    Activations Density 0.005%

    No Known Activations