Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 9100
    Prev
    Next
    INDEX
    Explanations

    phrases with unusual characters like 'âĢ' and 'Ļ'

    oai_token-act-pair · gpt-3.5-turbo

    instances of negation or denial in speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sights
    -0.70
     Mechdragon
    -0.69
    pmwiki
    -0.68
     Zup
    -0.66
    Buyable
    -0.66
    OTOS
    -0.66
    è»
    -0.65
    é¾
    -0.65
     Skydragon
    -0.65
     Taiwanese
    -0.64
    POSITIVE LOGITS
    £
    0.92
    ĸ
    0.90
    ĺ
    0.89
    ¤
    0.86
    ¼
    0.86
    Ļ
    0.86
    º
    0.85
    ghan
    0.83
    ///
    0.83
    §
    0.81
    Activations Density 0.244%

    No Known Activations