© 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. 17754
    Prev
    Next
    INDEX
    Explanations

    phrases related to community involvement and interaction

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to community-based organizations and activities

    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
     Mehran
    -0.85
     pedals
    -0.85
     typew
    -0.70
     expire
    -0.70
     torped
    -0.69
    washer
    -0.68
     pedal
    -0.67
     cartridges
    -0.67
    stroke
    -0.66
     Terminator
    -0.66
    POSITIVE LOGITS
    ¬¼
    1.06
     cohesion
    1.04
    Unity
    0.89
     communal
    0.86
     fostering
    0.85
     unity
    0.85
    community
    0.83
     cohesive
    0.83
     Forums
    0.80
     united
    0.80
    Activations Density 0.715%

    No Known Activations