© 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. 19326
    Prev
    Next
    INDEX
    Explanations

    Twitter handles of individuals

    oai_token-act-pair · gpt-3.5-turbo

    Twitter handles or usernames

    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
     Tone
    -0.88
     Ninth
    -0.87
     Resolution
    -0.84
     Hearts
    -0.84
     Direction
    -0.84
     Scheme
    -0.83
     Versus
    -0.83
     Enabled
    -0.80
    ï¸
    -0.79
     ACTIONS
    -0.79
    POSITIVE LOGITS
    podcast
    1.10
    music
    1.06
    obal
    1.05
    dc
    1.02
    mc
    1.00
    raham
    1.00
    oston
    0.99
    imore
    0.98
    politics
    0.98
    yond
    0.98
    Activations Density 0.132%

    No Known Activations