© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6805
    Prev
    Next
    INDEX
    Explanations

    names or proper nouns preceded by specific characters

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases that denote identities or roles

    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
     tests
    -0.77
     traps
    -0.77
     defences
    -0.75
     sites
    -0.75
     packets
    -0.72
     shelters
    -0.71
     defenses
    -0.71
     procedures
    -0.71
     ecosystems
    -0.70
     tunnels
    -0.69
    POSITIVE LOGITS
    founder
    1.14
    assador
    1.11
    utenant
    1.07
    artist
    1.04
    CEO
    1.03
    Actor
    1.03
    owner
    1.03
    Owner
    1.02
    Professor
    1.02
    director
    1.01
    Activations Density 0.767%

    No Known Activations