© 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
    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. 23629
    Prev
    Next
    INDEX
    Explanations

    phrases related to importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    phrases focused on the concept of what is important or significant

    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
    ãĥ³ãĤ¸
    -0.94
    ARP
    -0.83
    ript
    -0.76
    uthor
    -0.76
    guyen
    -0.76
    ãĥ¼ãĥ³
    -0.75
    ahime
    -0.74
    ULTS
    -0.73
     Labyrinth
    -0.72
    rys
    -0.71
    POSITIVE LOGITS
    lessly
    0.86
    enance
    0.73
    lessness
    0.73
     advis
    0.71
     aloud
    0.70
    rals
    0.69
     detrim
    0.67
    places
    0.66
     omin
    0.66
    safe
    0.66
    Activations Density 0.028%

    No Known Activations