© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 8176
    Prev
    Next
    INDEX
    Explanations

    tech-related abbreviations and acronyms

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations and acronyms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    esville
    -0.71
     seriousness
    -0.70
    hift
    -0.70
     Samoa
    -0.66
     Columb
    -0.66
     Colombia
    -0.65
    lihood
    -0.64
    thus
    -0.64
    20439
    -0.63
     Clown
    -0.62
    POSITIVE LOGITS
    RF
    1.08
    andom
    0.97
    raid
    0.89
    YL
    0.88
     RF
    0.86
    senal
    0.81
    UL
    0.81
    conservancy
    0.79
    Ĥª
    0.79
    ajo
    0.78
    Activations Density 0.007%

    No Known Activations