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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 7978
    Prev
    Next
    INDEX
    Explanations

    words related to striking or hitting something forcefully

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "strikes" in various contexts, particularly those linked to sports or actions

    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
    ħĭ
    -0.86
    regon
    -0.82
    ŀ
    -0.75
    adian
    -0.75
    anson
    -0.73
    raints
    -0.72
    umption
    -0.68
    ophers
    -0.67
    etsk
    -0.65
    opher
    -0.65
    POSITIVE LOGITS
    breakers
    0.93
    force
    0.91
     strike
    0.89
    out
    0.89
    ters
    0.81
     strikes
    0.81
    outs
    0.79
    strike
    0.78
     force
    0.78
    ting
    0.77
    Activations Density 0.018%

    No Known Activations