© 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. 2-RES-JB
    11. 12990
    Prev
    Next
    INDEX
    Explanations

    phrases with the special character "âĢ" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols

    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
    pei
    -0.73
     obscurity
    -0.72
     descending
    -0.69
    wagen
    -0.67
     charm
    -0.66
     semblance
    -0.64
     playbook
    -0.62
     bung
    -0.62
     division
    -0.61
     board
    -0.60
    POSITIVE LOGITS
    ł
    1.15
    ¹
    1.06
    ONSORED
    1.05
    ª
    0.92
    £
    0.91
    ij
    0.91
    IJ
    0.87
    Ī
    0.85
    ĺ
    0.85
    ı
    0.84
    Activations Density 0.153%

    No Known Activations