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. 10-RES-JB
    6. 20917
    Prev
    Next
    INDEX
    Explanations

    the word "Ant" with varying suffixes, including "-ic", "-ony", "-onio", "-es", "-elope", "-icip", "-ith", and "-on"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "Ant," indicating specific references or mentions of entities associated with that prefix

    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
    UGE
    -0.69
    UTION
    -0.68
     Stras
    -0.61
    mable
    -0.60
     Carib
    -0.59
    OUT
    -0.59
    OUP
    -0.58
     Trance
    -0.57
    glers
    -0.57
    çĭ
    -0.56
    POSITIVE LOGITS
    icip
    1.36
    oine
    1.29
    elope
    1.27
    icipated
    1.27
    iques
    1.26
    enna
    1.18
    agonists
    1.18
    ioch
    1.17
    onyms
    1.16
    idepress
    1.14
    Activations Density 0.023%

    No Known Activations