© 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. 1-RES-JB
    11. 16349
    Prev
    Next
    INDEX
    Explanations

    terms related to the Google Play Store

    oai_token-act-pair · gpt-3.5-turbo

    references to the Google Play store and related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.76
    ixed
    -0.73
    unal
    -0.73
    «ĺ
    -0.73
    ĸļ
    -0.72
    manuel
    -0.71
    orthodox
    -0.70
     tradem
    -0.69
     repatri
    -0.67
    porary
    -0.67
    POSITIVE LOGITS
    Play
    1.13
     Play
    1.10
     Plays
    1.00
    wright
    0.99
     Playing
    0.96
    plays
    0.92
     Solitaire
    0.88
    grounds
    0.87
    ground
    0.86
     Piano
    0.86
    Activations Density 0.011%

    No Known Activations