© 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. 7-RES-JB
    11. 11169
    Prev
    Next
    INDEX
    Explanations

    words related to technology and companies

    oai_token-act-pair · gpt-3.5-turbo

    unique or unusual naming conventions or titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dozen
    -0.69
    rongh
    -0.67
    rimp
    -0.64
     barg
    -0.64
    orsche
    -0.64
     grand
    -0.64
    rals
    -0.64
    gged
    -0.62
     cartels
    -0.60
     charact
    -0.58
    POSITIVE LOGITS
    Nation
    0.84
    Blog
    0.80
    Soft
    0.78
    Wiki
    0.73
     Enterprises
    0.73
    Vision
    0.72
     AFB
    0.72
     Productions
    0.72
    Tube
    0.72
    Lens
    0.70
    Activations Density 0.270%

    No Known Activations