© 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. 2-RES-JB
    6. 23679
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names related to a specific individual

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating support or endorsement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.75
    IFF
    -0.71
    uality
    -0.70
    PsyNetMessage
    -0.70
    ¬¼
    -0.69
    acan
    -0.69
    ARY
    -0.68
    acca
    -0.66
     juggling
    -0.66
    Joined
    -0.64
    POSITIVE LOGITS
    guard
    0.85
    lesi
    0.77
    ventus
    0.73
    port
    0.72
    nz
    0.71
    uploads
    0.71
    etheless
    0.70
    plate
    0.68
    restricted
    0.68
    los
    0.68
    Activations Density 0.000%

    No Known Activations