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. 3-RES-JB
    6. 8555
    Prev
    Next
    INDEX
    Explanations

    legal or financial terms related to seeking some sort of action or outcome

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "seeking" related to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    latest
    -0.68
    minus
    -0.67
    mson
    -0.65
    spin
    -0.65
    pron
    -0.64
     reckon
    -0.64
     Britann
    -0.63
    âĶĢâĶĢâĶĢâĶĢ
    -0.63
    pret
    -0.61
    sit
    -0.60
    POSITIVE LOGITS
     seeking
    0.81
     seekers
    0.78
     seek
    0.76
    emouth
    0.75
     unsuccessfully
    0.75
     seeks
    0.73
    orneys
    0.73
     glim
    0.73
    reprene
    0.72
     deadlines
    0.69
    Activations Density 0.021%

    No Known Activations