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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 23573
    Prev
    Next
    INDEX
    Explanations

    instances of the word "share" used in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the word "share" and its variations in different contexts

    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
    strom
    -0.76
    stal
    -0.74
    spection
    -0.68
    Champ
    -0.68
    kinson
    -0.67
    het
    -0.64
    umper
    -0.64
    susp
    -0.63
     Fist
    -0.62
    sted
    -0.62
    POSITIVE LOGITS
     share
    3.81
     shares
    2.53
    share
    2.44
     Share
    2.15
     sharing
    1.96
     shared
    1.64
    Share
    1.64
     Shares
    1.51
     Sharing
    1.50
    hare
    1.43
    Activations Density 0.020%

    No Known Activations