© 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. 6441
    Prev
    Next
    INDEX
    Explanations

    technical details or specifications

    oai_token-act-pair · gpt-3.5-turbo

    the character "ĸ" and its variations in different contexts

    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
    inctions
    -0.77
    raint
    -0.76
    raints
    -0.73
    ktop
    -0.73
    schild
    -0.69
    urchase
    -0.68
    olitan
    -0.68
    aspers
    -0.68
    shape
    -0.68
    arios
    -0.68
    POSITIVE LOGITS
    ĸ
    1.06
    ¶
    1.01
    ¾
    0.96
    åĤ
    0.95
    Ĺ
    0.94
    ï¸ı
    0.92
    ħĭ
    0.92
    ®
    0.91
    ¬
    0.88
    Ĩ
    0.87
    Activations Density 0.002%

    No Known Activations