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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 11180
    Prev
    Next
    INDEX
    Explanations

    words related to issues or challenges in various domains such as health, technology, human rights, and budgetary matters

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic and health-related issues

    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
     Pace
    -0.79
    »Ĵ
    -0.72
    cale
    -0.71
     VIDE
    -0.64
     Vide
    -0.64
    ertodd
    -0.63
    riel
    -0.63
    thouse
    -0.63
    encer
    -0.62
     Oval
    -0.61
    POSITIVE LOGITS
     problems
    1.43
     instability
    1.42
     failures
    1.39
     failure
    1.39
     deterioration
    1.39
     irregularities
    1.38
     woes
    1.37
     shortages
    1.36
     deficiency
    1.36
     disruption
    1.35
    Activations Density 0.693%

    No Known Activations