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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    6. 15050
    Prev
    Next
    INDEX
    Explanations

    words related to roughness or coarse textures

    oai_token-act-pair · gpt-3.5-turbo

    words containing the substring "gr" or related to Grand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     umb
    -0.64
     bloodstream
    -0.63
     iceberg
    -0.62
    ODUCT
    -0.59
     concess
    -0.59
    ĪĴ
    -0.59
     thor
    -0.58
     blockade
    -0.58
     disse
    -0.58
     deadline
    -0.58
    POSITIVE LOGITS
    eton
    0.94
    heit
    0.92
    ppe
    0.89
    veland
    0.81
    cale
    0.79
    steen
    0.79
    addy
    0.77
    liest
    0.72
    wine
    0.72
    ateurs
    0.72
    Activations Density 0.106%

    No Known Activations