© 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. 6-RES-JB
    6. 17589
    Prev
    Next
    INDEX
    Explanations

    locations and facilities where community events, services, and organizations take place

    oai_token-act-pair · gpt-3.5-turbo

    names of institutions and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    theless
    -1.07
    etheless
    -0.79
    ++;
    -0.75
    dated
    -0.72
     guessed
    -0.68
    rely
    -0.67
     cents
    -0.65
     embodiments
    -0.63
    agate
    -0.63
    atically
    -0.63
    POSITIVE LOGITS
     Festival
    1.10
     Complex
    1.09
     Settlement
    1.05
     Facility
    0.99
     Collective
    0.97
     Clinic
    0.96
     Registry
    0.94
     Prize
    0.94
     Museum
    0.94
     Collection
    0.93
    Activations Density 0.309%

    No Known Activations