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. 4-RES-JB
    6. 21024
    Prev
    Next
    INDEX
    Explanations

    metaphorical phrases related to rewards and punishments

    oai_token-act-pair · gpt-3.5-turbo

    metaphorical expressions related to various concepts or ideas

    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
    AMI
    -0.61
     Superintendent
    -0.60
    PLIED
    -0.60
     Norn
    -0.58
    ARB
    -0.56
     Bristol
    -0.56
    BU
    -0.55
    Express
    -0.55
     Editors
    -0.54
    Material
    -0.54
    POSITIVE LOGITS
    emonic
    0.87
    bowl
    0.76
    pie
    0.73
    headed
    0.71
    cake
    0.66
    anging
    0.66
    arious
    0.64
    cakes
    0.63
    belt
    0.62
    kefeller
    0.62
    Activations Density 0.491%

    No Known Activations