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. 2-RES-JB
    6. 139
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "pub," which could be related to publishing or publications

    oai_token-act-pair · gpt-4-turbo

    websites or online publications

    oai_token-act-pair · gpt-3.5-turbo

    references to publishing entities or platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Isles
    -0.85
     ANGEL
    -0.79
     Spears
    -0.76
    IRD
    -0.75
    OHN
    -0.74
     Daytona
    -0.72
     Esper
    -0.71
     Aires
    -0.69
     Ellis
    -0.69
     CHRIST
    -0.67
    POSITIVE LOGITS
    lishing
    1.60
    lisher
    1.60
    lish
    1.39
    lique
    1.33
    lishes
    1.27
    escent
    1.18
    pub
    1.12
    Pub
    1.08
    lik
    1.01
    keys
    0.91
    Activations Density 0.007%

    No Known Activations