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. 6-RES-JB
    6. 2157
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning a spatial location in relation to a person or object

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or location in relation to "back of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BIL
    -0.82
     Cosponsors
    -0.80
    PF
    -0.75
    merce
    -0.69
    Äĩ
    -0.68
    Specific
    -0.67
    NetMessage
    -0.66
    lda
    -0.66
    IRC
    -0.65
    nown
    -0.64
    POSITIVE LOGITS
     cylinders
    0.68
     pack
    0.63
     porch
    0.62
     packet
    0.62
    cards
    0.62
    coat
    0.61
     sofa
    0.61
     Fraz
    0.60
    track
    0.60
     package
    0.59
    Activations Density 0.056%

    No Known Activations