© 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. 15328
    Prev
    Next
    INDEX
    Explanations

    locations and events

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations or proper nouns related to places

    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
    odic
    -0.67
    rodu
    -0.67
    xual
    -0.67
    anian
    -0.65
    ewitness
    -0.65
    ilitary
    -0.63
     penet
    -0.61
    agonist
    -0.59
    ailable
    -0.58
    odan
    -0.58
    POSITIVE LOGITS
     TBA
    0.80
     Bohem
    0.78
     TBD
    0.73
     NY
    0.73
     Angeles
    0.72
     Spokane
    0.71
     Niagara
    0.70
     Shoals
    0.70
     Tampa
    0.70
     Albany
    0.69
    Activations Density 0.155%

    No Known Activations