© 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. 11-RES-JB
    6. 9930
    Prev
    Next
    INDEX
    Explanations

    technical terms and jargon related to electrical engineering and physical conditions

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to sensory perceptions and physical conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     commercially
    -0.71
     nationally
    -0.69
     internationally
    -0.67
     professionally
    -0.67
     privately
    -0.66
     legally
    -0.66
     economically
    -0.65
     National
    -0.65
     homegrown
    -0.64
     financially
    -0.63
    POSITIVE LOGITS
    ersion
    1.15
    terness
    1.07
    leness
    1.04
    idity
    1.01
    vation
    1.00
     interruption
    0.98
    oxicity
    0.98
    eness
    0.97
    ipation
    0.97
    iness
    0.96
    Activations Density 0.641%

    No Known Activations