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. 4-RES-JB
    6. 15048
    Prev
    Next
    INDEX
    Explanations

    keywords related to gathering or collecting information, objects, or data

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to data collection and gathering

    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
    ahime
    -0.78
    rican
    -0.75
    ĸļ
    -0.74
    facing
    -0.72
    lander
    -0.72
    ogun
    -0.71
    ua
    -0.69
    seek
    -0.67
    ĪĴ
    -0.67
    Ī
    -0.67
    POSITIVE LOGITS
    DragonMagazine
    0.84
     jars
    0.76
    abytes
    0.76
     shelves
    0.71
     belongings
    0.70
    metadata
    0.69
     fragments
    0.69
     microscopic
    0.68
    artifacts
    0.67
     souven
    0.66
    Activations Density 0.350%

    No Known Activations