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. 8456
    Prev
    Next
    INDEX
    Explanations

    the word "ico" followed by a number value of 9 or 10

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ico" and its variations, suggesting a focus on topics related to "ico" terminology, likely in a cryptocurrency or blockchain context

    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
     Rasm
    -0.68
     err
    -0.67
     pointer
    -0.65
     pointers
    -0.65
     favour
    -0.62
     wed
    -0.62
     Prophet
    -0.60
     Allah
    -0.59
     digit
    -0.59
     Thorn
    -0.59
    POSITIVE LOGITS
    ico
    4.58
    ICO
    2.21
    ica
    1.71
    icon
    1.47
    ican
    1.44
    ique
    1.43
    icas
    1.41
    iques
    1.30
    ici
    1.29
    icus
    1.28
    Activations Density 0.015%

    No Known Activations