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. 11-RES-JB
    6. 10931
    Prev
    Next
    INDEX
    Explanations

    action verbs related to physical movement and interaction

    oai_token-act-pair · gpt-3.5-turbo

    action verbs related to movement and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SPONSORED
    -0.76
     Âł Âł Âł Âł
    -0.68
    ization
    -0.65
     Âł Âł Âł Âł Âł Âł Âł Âł
    -0.62
    ãĤµ
    -0.61
     Independence
    -0.60
    ãĥĦ
    -0.59
    isation
    -0.58
     anten
    -0.57
     Fiji
    -0.57
    POSITIVE LOGITS
    ling
    2.39
    led
    2.29
    les
    2.24
    lers
    2.06
    ler
    1.84
    lement
    1.79
    lings
    1.68
    lements
    1.54
    le
    1.50
    leground
    1.45
    Activations Density 0.122%

    No Known Activations