Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 10614
    Prev
    Next
    INDEX
    Explanations

    words related to specific names and locations, particularly focusing on German-sounding names

    oai_token-act-pair · gpt-3.5-turbo

    names of people and entities mentioned within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tycoon
    -0.64
    ity
    -0.64
    itions
    -0.60
    ingly
    -0.60
    ioxide
    -0.60
    Downloadha
    -0.59
    ibly
    -0.57
    icts
    -0.57
    izards
    -0.57
     Mov
    -0.57
    POSITIVE LOGITS
    berg
    1.13
    baum
    1.05
    hof
    1.04
    wald
    1.03
    lander
    1.00
    mann
    0.99
    STE
    0.97
    feld
    0.96
    hoff
    0.95
    heimer
    0.93
    Activations Density 0.088%

    No Known Activations