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. 10-RES-JB
    6. 3870
    Prev
    Next
    INDEX
    Explanations

    verbs or phrases related to actions directed towards a specific goal or target

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating intended actions or objectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Optional
    -0.74
     hesitate
    -0.69
    minus
    -0.69
    wine
    -0.67
    zek
    -0.67
    NESS
    -0.66
    ledged
    -0.66
    wait
    -0.65
    asca
    -0.65
    owa
    -0.65
    POSITIVE LOGITS
     improving
    1.68
     preventing
    1.67
     preserving
    1.63
     protecting
    1.56
     combating
    1.55
     ensuring
    1.53
     reducing
    1.51
     promoting
    1.50
     restoring
    1.50
     eliminating
    1.50
    Activations Density 0.191%

    No Known Activations