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. 2326
    Prev
    Next
    INDEX
    Explanations

    words related to replenishment and nourishment

    oai_token-act-pair · gpt-3.5-turbo

    words related to replenishment and restoration

    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
    MQ
    -0.69
    WER
    -0.68
    Film
    -0.66
    Video
    -0.66
    crop
    -0.66
    Viol
    -0.66
    Magikarp
    -0.65
     Fate
    -0.64
     ACTION
    -0.64
     Personality
    -0.64
    POSITIVE LOGITS
    ishment
    1.82
    ished
    1.69
    ishing
    1.54
    ishers
    1.49
    isher
    1.44
    ishes
    1.39
    ishable
    1.29
    itions
    1.17
    ition
    1.15
    inished
    1.08
    Activations Density 0.026%

    No Known Activations