© 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. 2-RES-JB
    11. 23666
    Prev
    Next
    INDEX
    Explanations

    specific names, likely related to a movie or a film project

    oai_token-act-pair · gpt-3.5-turbo

    key names and terms related to film production and sports commentary

    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
    hei
    -0.73
    ãĤŃ
    -0.67
     Mbps
    -0.66
    wife
    -0.65
    aceous
    -0.64
    ido
    -0.64
    orce
    -0.64
     Parenthood
    -0.63
     myster
    -0.62
    oret
    -0.62
    POSITIVE LOGITS
    schild
    0.87
     dart
    0.83
     Barkley
    0.81
    ozy
    0.80
    jet
    0.72
    obin
    0.71
    poon
    0.70
    lain
    0.69
    osal
    0.68
    arters
    0.67
    Activations Density 0.017%

    No Known Activations