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. 0-RES-JB
    6. 8500
    Prev
    Next
    INDEX
    Explanations

    words related to umbrellas and various text related to the context of umbrellas, and words related to immaturity and tethering

    oai_token-act-pair · gpt-3.5-turbo

    references to umbrellas and themes of restriction or confinement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    few
    -0.65
    meet
    -0.62
    cca
    -0.62
    Si
    -0.62
    vi
    -0.62
    Minnesota
    -0.60
    mates
    -0.58
    Kansas
    -0.57
    vell
    -0.57
     judges
    -0.56
    POSITIVE LOGITS
     umb
    2.67
     Umb
    1.49
     tether
    1.00
     ì
    1.00
     Mub
    0.81
     immature
    0.78
     Prototype
    0.74
     ILCS
    0.74
    NetMessage
    0.73
    actionDate
    0.68
    Activations Density 0.008%

    No Known Activations