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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 5-RES-JB
    6. 20303
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical struggle or conflict

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "str" and related forms, suggesting a focus on words indicating strength or structural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peat
    -0.74
    shots
    -0.74
    pei
    -0.73
    jay
    -0.72
    boys
    -0.70
    manship
    -0.67
    ¥µ
    -0.67
    hyde
    -0.66
    bear
    -0.66
    hide
    -0.65
    POSITIVE LOGITS
    ategy
    1.25
    ained
    1.25
    ainer
    1.19
    ategic
    1.16
    aining
    1.11
    uments
    1.03
    icken
    1.03
    anded
    1.01
    aints
    0.99
    angled
    0.98
    Activations Density 0.013%

    No Known Activations