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. 3-RES-JB
    6. 11080
    Prev
    Next
    INDEX
    Explanations

    user profiles including the mention of the number of posts made by the user

    oai_token-act-pair · gpt-3.5-turbo

    references to the number of posts in a profile or blog context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bhar
    -0.86
    bill
    -0.72
     Brill
    -0.70
    ISA
    -0.69
    ologically
    -0.69
    isen
    -0.69
    rina
    -0.68
    bid
    -0.68
    ONSORED
    -0.67
    phe
    -0.65
    POSITIVE LOGITS
     Posts
    1.17
     Joined
    1.09
    Posts
    0.87
    reply
    0.82
     Offense
    0.79
     posts
    0.79
    greSQL
    0.76
     Blog
    0.74
    ertodd
    0.74
    Thread
    0.74
    Activations Density 0.019%

    No Known Activations