© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 6900
    Prev
    Next
    INDEX
    Explanations

    keywords related to various events and topics, potentially related to news or articles

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, particularly periods and lists

    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
     signalling
    -0.76
     designated
    -0.72
    ollen
    -0.72
     neglig
    -0.71
    TPS
    -0.69
    gress
    -0.68
    ère
    -0.68
     maiden
    -0.67
     favoured
    -0.67
     allot
    -0.67
    POSITIVE LOGITS
     Written
    1.18
     VIDEOS
    1.18
     Subscribe
    1.15
     Plus
    1.14
     VIDE
    1.13
     Learn
    1.13
     Reporter
    1.08
     Topics
    1.08
     Highlights
    1.07
     Listen
    1.06
    Activations Density 0.388%

    No Known Activations