© 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. 23531
    Prev
    Next
    INDEX
    Explanations

    phrases related to strong smells

    oai_token-act-pair · gpt-3.5-turbo

    words related to the sense of smell

    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
    TAIN
    -0.70
    EMENT
    -0.65
     Cerberus
    -0.64
     YPG
    -0.63
    RELATED
    -0.62
    ITAL
    -0.62
    cair
    -0.61
     RTX
    -0.61
     Wis
    -0.60
     GIF
    -0.60
    POSITIVE LOGITS
    ooth
    1.38
    oke
    1.18
    Sm
    1.08
    oking
    1.07
    oky
    1.04
    ugg
    1.02
    udge
    0.98
    itten
    0.97
    attering
    0.96
    sm
    0.95
    Activations Density 0.004%

    No Known Activations