© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 15345
    Prev
    Next
    INDEX
    Explanations

    <strong>information related to user profiles and their posts, most likely in an online community or forum setting.</strong>

    oai_token-act-pair · gpt-3.5-turbo

    references to user profiles and the number of posts made by users

    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
    flies
    -0.72
    orman
    -0.70
    ILY
    -0.68
    mere
    -0.68
    selves
    -0.67
    HOU
    -0.67
    ograms
    -0.67
    ryn
    -0.64
    UC
    -0.63
    fits
    -0.62
    POSITIVE LOGITS
     Joined
    1.03
     Last
    0.91
     Posts
    0.86
     Blog
    0.78
     Posted
    0.77
     Edited
    0.76
     Played
    0.74
     Reply
    0.74
     #
    0.74
    Reply
    0.73
    Activations Density 0.011%

    No Known Activations