© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 3771
    Prev
    Next
    INDEX
    Explanations

    personal actions and events associated with an individual's story or narrative

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific person involved in a series of criminal events

    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
    âĺħâĺħ
    -0.75
     Romantic
    -0.69
     Gregg
    -0.65
     Optim
    -0.65
     Clair
    -0.64
    BALL
    -0.64
     Logo
    -0.63
     Chaser
    -0.62
     Subtle
    -0.62
    Real
    -0.62
    POSITIVE LOGITS
    zbollah
    1.03
     pleaded
    0.99
     fled
    0.96
     reportedly
    0.94
     underwent
    0.93
     allegedly
    0.90
    'd
    0.89
     drove
    0.89
     testified
    0.89
     bailed
    0.87
    Activations Density 0.333%

    No Known Activations