© 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. 8-RES-JB
    11. 2759
    Prev
    Next
    INDEX
    Explanations

    information related to posts made in online forums or communities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Posts" and track post counts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bhar
    -0.71
    mere
    -0.64
     neglig
    -0.62
    rette
    -0.62
    flies
    -0.61
     energies
    -0.61
    orman
    -0.60
    rium
    -0.60
     consultants
    -0.59
    Aid
    -0.59
    POSITIVE LOGITS
     Joined
    1.05
     Posts
    0.95
    reply
    0.86
     Last
    0.82
    Reply
    0.79
     Edited
    0.74
    ategory
    0.74
     Why
    0.72
     Offense
    0.71
    Thread
    0.70
    Activations Density 0.017%

    No Known Activations