© 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. 20879
    Prev
    Next
    INDEX
    Explanations

    technical terms related to physical characteristics or attributes

    oai_token-act-pair · gpt-3.5-turbo

    references to various properties of materials and systems

    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
    icago
    -0.76
    bone
    -0.76
    ansen
    -0.69
    scl
    -0.68
    ACTED
    -0.68
    atre
    -0.66
     Nadu
    -0.65
    avez
    -0.62
    bones
    -0.60
    MAX
    -0.59
    POSITIVE LOGITS
     properties
    0.99
    ality
    0.83
    uation
    0.81
    properties
    0.81
    ECT
    0.77
    ious
    0.75
     Properties
    0.74
    Changed
    0.74
    ter
    0.73
    iveness
    0.72
    Activations Density 0.022%

    No Known Activations