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. 23101
    Prev
    Next
    INDEX
    Explanations

    references to physical substances such as water, moisture, fat, and ash

    oai_token-act-pair · gpt-3.5-turbo

    terms related to water and its properties in various contexts

    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
    cffffcc
    -0.78
    odore
    -0.78
     Dare
    -0.70
    umbn
    -0.69
    saf
    -0.69
     Smile
    -0.67
     NCT
    -0.64
     Serious
    -0.64
     Fidel
    -0.64
    FINE
    -0.63
    POSITIVE LOGITS
     molecules
    1.38
     particles
    1.25
     deposits
    1.16
     grains
    1.11
     ions
    1.10
     residues
    1.08
     dioxide
    1.08
     fragments
    1.07
     buildup
    1.06
     fibers
    1.06
    Activations Density 0.203%

    No Known Activations