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. 8-RES-JB
    6. 20946
    Prev
    Next
    INDEX
    Explanations

    phrases or proper names containing the token "ick"

    oai_token-act-pair · gpt-3.5-turbo

    variations of the name "Rick."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.76
    ãĤ£
    -0.75
    PsyNetMessage
    -0.73
    ãģ®å
    -0.71
    EMBER
    -0.70
    ãĥģ
    -0.67
    IFA
    -0.66
    orescence
    -0.65
    oding
    -0.65
    ONT
    -0.64
    POSITIVE LOGITS
    erman
    1.01
    etts
    1.00
    ety
    0.99
    leness
    0.98
    eter
    0.95
    ering
    0.94
    eters
    0.93
    ery
    0.93
    ett
    0.92
    icks
    0.90
    Activations Density 0.054%

    No Known Activations