© 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
    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. 7590
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports and activities

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations or regions

    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
    anwhile
    -0.77
    etheus
    -0.65
    Reilly
    -0.64
     enthusi
    -0.58
    avorite
    -0.56
    ãĥ¼ãĥĨ
    -0.55
    emis
    -0.55
    atever
    -0.55
    gerald
    -0.54
    miah
    -0.53
    POSITIVE LOGITS
     [+
    0.77
    É
    0.65
     ·
    0.63
     -->
    0.62
     âĢ
    0.61
     âĻ
    0.60
     */
    0.60
     ãģ
    0.59
     âĢº
    0.58
     å
    0.57
    Activations Density 0.774%

    No Known Activations