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. 7-RES-JB
    6. 3357
    Prev
    Next
    INDEX
    Explanations

    actions related to carrying out a specific objective

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions or conditions that follow a specified order or protocol

    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
    tex
    -0.71
    irted
    -0.67
    ider
    -0.66
    redited
    -0.64
    nis
    -0.60
    ritten
    -0.60
    milo
    -0.60
    ky
    -0.60
    etheless
    -0.59
    tek
    -0.59
    POSITIVE LOGITS
     Osw
    0.90
    lies
    0.69
    ppel
    0.69
     bolster
    0.67
     fulfillment
    0.66
     fres
    0.65
    meal
    0.64
     ensure
    0.64
    liness
    0.63
     alleviate
    0.63
    Activations Density 0.017%

    No Known Activations