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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 11732
    Prev
    Next
    INDEX
    Explanations

    words related to physical and athletic movements, particularly those involving somersaults

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "some" and its implications in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UID
    -0.85
    holder
    -0.74
    ãĥ¼ãĥĨãĤ£
    -0.74
    HOME
    -0.70
    ULTS
    -0.66
    FER
    -0.62
     evict
    -0.62
    ILD
    -0.61
     Veronica
    -0.61
     Addiction
    -0.61
    POSITIVE LOGITS
     som
    0.93
    stem
    0.89
    ber
    0.87
    atos
    0.85
    obile
    0.81
    rien
    0.81
     skelet
    0.81
    asa
    0.81
    othe
    0.81
    othy
    0.80
    Activations Density 0.009%

    No Known Activations