© 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. 8-RES-JB
    11. 6299
    Prev
    Next
    INDEX
    Explanations

    common words used in conjunction with 'so' or 'does'

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases that indicate agreement or shared experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istries
    -0.76
    QB
    -0.74
    colo
    -0.65
     shenan
    -0.64
     didnt
    -0.63
     misunder
    -0.61
    ista
    -0.59
    Words
    -0.59
    direction
    -0.59
    ified
    -0.58
    POSITIVE LOGITS
     others
    0.76
     countless
    0.73
     Memories
    0.71
    hap
    0.65
     many
    0.65
     anyone
    0.63
     ours
    0.63
     Nost
    0.60
    ection
    0.59
     Sanct
    0.59
    Activations Density 0.075%

    No Known Activations