© 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. 11-RES-JB
    11. 7045
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific research and investigation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to research objectives and experimental methods

    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
     Armageddon
    -0.83
    Enlarge
    -0.72
    atron
    -0.70
     Canaveral
    -0.68
    leans
    -0.66
    abouts
    -0.62
    cair
    -0.61
    Downloadha
    -0.61
     Think
    -0.61
     Quote
    -0.61
    POSITIVE LOGITS
    Methods
    1.15
    METHOD
    1.02
    Materials
    0.95
     epidem
    0.91
     hypothesized
    0.91
    clinical
    0.91
    spective
    0.91
     Methods
    0.90
     meta
    0.89
     eluc
    0.88
    Activations Density 0.205%

    No Known Activations