Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 12505
    Prev
    Next
    INDEX
    Explanations

    complex questions involving potential scenarios or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    key terms related to economics and governance

    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
    ces
    -0.68
    76561
    -0.66
    bidden
    -0.61
    GGGGGGGG
    -0.60
     Cosponsors
    -0.60
    specified
    -0.60
     Heads
    -0.58
    CI
    -0.58
    ares
    -0.56
    poses
    -0.55
    POSITIVE LOGITS
     survive
    1.23
     be
    1.16
     prevail
    1.10
     become
    1.09
     succeed
    1.07
     prove
    1.06
     evolve
    1.06
     convince
    1.04
     differ
    1.04
     decide
    1.03
    Activations Density 0.183%

    No Known Activations