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. 16620
    Prev
    Next
    INDEX
    Explanations

    descriptions of the size, weight, and construction materials of objects

    oai_token-act-pair · gpt-3.5-turbo

    phrases that refer to objects or devices

    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
    911
    -0.66
    dding
    -0.65
    course
    -0.64
     Corpus
    -0.64
    traumatic
    -0.63
    castle
    -0.62
     Guant
    -0.62
    priv
    -0.62
     Union
    -0.61
    Priv
    -0.60
    POSITIVE LOGITS
    unes
    1.03
    chy
    1.01
     seems
    1.00
    alian
    1.00
    'll
    0.99
    self
    0.98
    theless
    0.96
     doesnt
    0.90
    's
    0.89
     appears
    0.88
    Activations Density 0.282%

    No Known Activations