Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 17372
    Prev
    Next
    INDEX
    Explanations

    phrases related to attempts or retrying something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating an attempt to resolve an issue or retry an action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kees
    -0.71
    neapolis
    -0.62
     foremost
    -0.62
    geist
    -0.60
     Gathering
    -0.59
    owicz
    -0.58
    ©¶æ
    -0.57
     Lantern
    -0.56
    icipated
    -0.55
    imer
    -0.54
    POSITIVE LOGITS
     nor
    0.72
     subscribing
    0.69
     Cancel
    0.67
    qus
    0.67
     anymore
    0.66
     typing
    0.64
     Submit
    0.63
     captcha
    0.62
     Invalid
    0.61
     php
    0.60
    Activations Density 0.023%

    No Known Activations