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. 12-RES-JB
    6. 15083
    Prev
    Next
    INDEX
    Explanations

    phrases related to probability or uncertainty, as well as words related to dietary supplements

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to probability and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Siege
    -0.66
    sis
    -0.64
     Peninsula
    -0.64
    ways
    -0.63
     Brotherhood
    -0.63
     Lumpur
    -0.63
     Phillips
    -0.60
    cross
    -0.59
    chest
    -0.59
    plate
    -0.58
    POSITIVE LOGITS
    abilities
    1.25
    iferation
    1.17
    ifer
    1.16
    abil
    1.14
    aband
    1.13
    itely
    1.10
    arian
    1.05
    iotics
    1.03
    alf
    1.00
    arians
    1.00
    Activations Density 0.132%

    No Known Activations