© 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. 2-RES-JB
    11. 8423
    Prev
    Next
    INDEX
    Explanations

    language related to sending or conveying something from one place to another

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "send."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urity
    -0.71
    minster
    -0.67
    ItemTracker
    -0.65
    Sov
    -0.61
    Fram
    -0.60
     Guth
    -0.60
    etus
    -0.60
    phe
    -0.58
    profit
    -0.58
    BuyableInstoreAndOnline
    -0.56
    POSITIVE LOGITS
    inel
    0.97
     send
    0.85
    keys
    0.82
    entary
    0.79
     Send
    0.78
    imental
    0.76
    vertis
    0.76
    soever
    0.76
    forward
    0.76
     sent
    0.76
    Activations Density 0.024%

    No Known Activations