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. 18663
    Prev
    Next
    INDEX
    Explanations

    words related to deliberate actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intentionality and deliberate actions

    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
     Tycoon
    -0.87
    ĪĴ
    -0.77
    elo
    -0.71
     Solitaire
    -0.70
    iao
    -0.68
     Parables
    -0.68
    abies
    -0.67
    WB
    -0.67
     Babe
    -0.66
     Dogs
    -0.65
    POSITIVE LOGITS
     deliberate
    0.86
     intentional
    0.86
    ãĥĩãĤ£
    0.78
    ãĥĥãĤ¯
    0.72
    ãĤ°
    0.71
     actionGroup
    0.70
     attempt
    0.70
    ãĥĨ
    0.68
    atory
    0.67
     wrongdoing
    0.67
    Activations Density 0.016%

    No Known Activations