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. 11-RES-JB
    6. 19123
    Prev
    Next
    INDEX
    Explanations

    words related to stability and solidity

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of solidity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    xual
    -0.76
    Hop
    -0.70
     Reeves
    -0.65
     Incarnation
    -0.63
    hop
    -0.63
     wisely
    -0.60
     Loft
    -0.60
     Crowley
    -0.59
    plugins
    -0.59
     Suite
    -0.58
    POSITIVE LOGITS
    ified
    1.52
    ifying
    1.44
    arity
    1.36
    ifies
    1.32
    GoldMagikarp
    1.31
    ify
    1.24
    ification
    1.19
    IFIED
    1.10
    ifiers
    1.07
    ity
    1.06
    Activations Density 0.051%

    No Known Activations