© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1900
    Prev
    Next
    INDEX
    Explanations

    references to proprietary information or products

    oai_token-act-pair · gpt-3.5-turbo

    terms related to proprietary rights and intellectual property

    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
    ership
    -0.94
    othy
    -0.82
    neau
    -0.77
    itri
    -0.77
    emouth
    -0.76
    aler
    -0.75
    stad
    -0.75
     [+
    -0.75
    ocaust
    -0.74
    noon
    -0.73
    POSITIVE LOGITS
     proprietary
    0.78
     technologies
    0.69
     patented
    0.67
     IPM
    0.66
    ModLoader
    0.66
     codec
    0.65
     oxy
    0.65
     treatments
    0.65
     algorithms
    0.64
     transcription
    0.64
    Activations Density 0.081%

    No Known Activations