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. 0-RES-JB
    6. 3066
    Prev
    Next
    INDEX
    Explanations

    successors or heirs to a position or role

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "successor" and related terms indicating successors or heirs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pees
    -0.73
    ambo
    -0.64
    stuff
    -0.59
    forest
    -0.57
    poons
    -0.57
     bars
    -0.57
    icing
    -0.57
    points
    -0.56
    Tips
    -0.56
    views
    -0.56
    POSITIVE LOGITS
     successor
    4.15
     successors
    3.02
     predecessor
    2.01
     heir
    1.75
     replacement
    1.64
     descendant
    1.50
     heirs
    1.45
     sequel
    1.42
     predecessors
    1.40
     replacements
    1.37
    Activations Density 0.014%

    No Known Activations