© 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. 16819
    Prev
    Next
    INDEX
    Explanations

    statements related to sending messages or taking action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sending" in various contexts

    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
    ãĤ¨
    -0.65
    cube
    -0.64
     Guth
    -0.62
    Fram
    -0.62
    lihood
    -0.62
     Alban
    -0.60
    ItemTracker
    -0.60
    minster
    -0.59
    ERO
    -0.59
     Hartford
    -0.58
    POSITIVE LOGITS
    lyak
    0.86
    maid
    0.84
    inel
    0.82
     mosqu
    0.80
    entary
    0.79
    ezvous
    0.78
    imental
    0.76
    redients
    0.75
    raw
    0.74
     send
    0.74
    Activations Density 0.009%

    No Known Activations