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. 9-RES-JB
    6. 8063
    Prev
    Next
    INDEX
    Explanations

    proper nouns or named entities

    oai_token-act-pair · gpt-3.5-turbo

    tokens indicating the end of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CPR
    -0.69
     crib
    -0.66
     Ribbon
    -0.64
     psycho
    -0.63
     unrestricted
    -0.63
     Strip
    -0.62
     stressed
    -0.61
     Triangle
    -0.60
    tops
    -0.60
     Proto
    -0.60
    POSITIVE LOGITS
    ixty
    1.40
    olutions
    1.32
    omew
    1.32
    ESSION
    1.29
    atisf
    1.28
    ierra
    1.28
    ometime
    1.28
    atellite
    1.27
    ustain
    1.26
    essions
    1.23
    Activations Density 0.052%

    No Known Activations