© 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. 23380
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases containing the word "Sent."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Sent" 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
     Galile
    -0.69
    ARDS
    -0.69
     UNESCO
    -0.67
    ARD
    -0.65
    ãģį
    -0.65
    OSS
    -0.65
     Dob
    -0.64
    orsi
    -0.64
    ILD
    -0.63
    WAYS
    -0.63
    POSITIVE LOGITS
     Sent
    1.36
    Sent
    1.22
    sent
    1.15
    inel
    1.11
    iments
    0.98
    imental
    0.95
     confir
    0.88
    enced
    0.86
    encing
    0.86
    entious
    0.86
    Activations Density 0.009%

    No Known Activations