© 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. 3-RES-JB
    11. 14751
    Prev
    Next
    INDEX
    Explanations

    references to specific financial institutions or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to financial organizations or commissions

    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
    rawdownloadcloneembedreportprint
    -0.80
    Downloadha
    -0.73
    ãĤ°
    -0.68
    Magikarp
    -0.67
    ãĥĦ
    -0.66
    felt
    -0.65
    å°Ĩ
    -0.65
    acity
    -0.63
    ãĤ®
    -0.62
    é¾įå¥ij士
    -0.62
    POSITIVE LOGITS
    incinn
    0.95
    ranch
    0.88
    avorite
    0.86
    yre
    0.85
    rosis
    0.85
    ritical
    0.84
    amily
    0.83
    entanyl
    0.82
    erm
    0.81
    ayette
    0.79
    Activations Density 0.005%

    No Known Activations