© 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. 23007
    Prev
    Next
    INDEX
    Explanations

    locations or specific places mentioned in texts

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal experiences or observations

    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
    interstitial
    -0.76
    iru
    -0.71
     celebrations
    -0.69
    apo
    -0.68
    Delivery
    -0.66
    Adds
    -0.63
     energetic
    -0.60
     delivering
    -0.59
     advancing
    -0.59
     transporting
    -0.59
    POSITIVE LOGITS
    ©¶æ
    0.95
     firsthand
    0.84
    umerable
    0.82
    tested
    0.77
    ocrates
    0.75
    76561
    0.73
     carefully
    0.73
    oscope
    0.71
     declass
    0.71
     quizz
    0.70
    Activations Density 0.586%

    No Known Activations