© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7135
    Prev
    Next
    INDEX
    Explanations

    words ending with "smith"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "smith" 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
    pty
    -0.64
     Paragu
    -0.64
     Opposition
    -0.64
     Pad
    -0.62
     Patients
    -0.61
    condition
    -0.61
     Legisl
    -0.60
     patients
    -0.60
     ALS
    -0.60
     repressive
    -0.59
    POSITIVE LOGITS
    mith
    1.51
    sonian
    1.34
    smanship
    1.12
    smith
    1.05
    uria
    0.98
    ocity
    0.90
    uin
    0.89
    ovember
    0.87
    heim
    0.85
    doms
    0.85
    Activations Density 0.007%

    No Known Activations