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. 0-RES-JB
    6. 14309
    Prev
    Next
    INDEX
    Explanations

    terms related to crossing or crossing off items from a list

    oai_token-act-pair · gpt-3.5-turbo

    references to crossing lines or boundaries, often in the context of transitions or influences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.79
     opted
    -0.63
    andum
    -0.62
    console
    -0.61
     avail
    -0.61
     secure
    -0.60
     err
    -0.60
    undle
    -0.60
    Dispatch
    -0.60
    ahar
    -0.60
    POSITIVE LOGITS
     crosses
    2.87
     influences
    2.23
     touches
    1.59
     alters
    1.34
     converts
    1.21
     mixes
    1.21
     casts
    1.20
     scares
    1.19
     embraces
    1.18
     shines
    1.15
    Activations Density 0.029%

    No Known Activations