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. 4-RES-JB
    6. 18009
    Prev
    Next
    INDEX
    Explanations

    words related to materials, science, and academic fields with a focus on the prefix "meta-" or variations like "metamaterial" and physical properties like "glass."

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specific materials and references to the Seminole community

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

    No Comments

    Negative Logits
    Allen
    -0.76
    DERR
    -0.65
    Madison
    -0.65
    RT
    -0.64
    dit
    -0.64
    ELL
    -0.62
    Kate
    -0.61
     Compliance
    -0.60
     apt
    -0.59
    NOW
    -0.59
    POSITIVE LOGITS
    ical
    0.98
    icism
    0.96
    icals
    0.91
    ifiers
    0.89
    astic
    0.88
    ographs
    0.86
    ificent
    0.84
    uchin
    0.82
    ICAL
    0.81
    iques
    0.81
    Activations Density 0.039%

    No Known Activations