© 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. 10273
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences expressing unity or collective belonging

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing inclusivity or collective involvement

    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
    fecture
    -0.64
    SHIP
    -0.63
    kson
    -0.62
    iggurat
    -0.62
    kamp
    -0.62
    notation
    -0.61
    potion
    -0.61
    culosis
    -0.61
    ernaut
    -0.60
    only
    -0.59
    POSITIVE LOGITS
     stakeholders
    1.07
     parties
    1.03
     sorts
    1.02
    ocating
    1.02
     involved
    1.01
     kinds
    1.01
     facets
    0.92
     sides
    0.91
     genders
    0.89
    igators
    0.89
    Activations Density 0.081%

    No Known Activations