© 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 EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5099
    Prev
    Next
    INDEX
    Explanations

    nouns related to items or entities

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to entities and objects in various contexts

    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
     Dhabi
    -0.71
    \\\\\\\\
    -0.69
    UTERS
    -0.64
     Disorder
    -0.63
    âĢ¢âĢ¢
    -0.62
     Ventures
    -0.60
    ALLY
    -0.60
     Zealand
    -0.59
    mington
    -0.58
    BALL
    -0.58
    POSITIVE LOGITS
     themselves
    1.19
    etter
    1.13
    mith
    1.12
    etting
    1.03
    cape
    1.01
    linger
    1.00
    hip
    0.99
    ensitive
    0.98
    heet
    0.97
    ettings
    0.95
    Activations Density 0.365%

    No Known Activations