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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 20963
    Prev
    Next
    INDEX
    Explanations

    phrases related to speech or quotes, potentially in a context of intensity or emotion

    oai_token-act-pair · gpt-3.5-turbo

    the special character 'âĢ' in the text

    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
     tram
    -0.75
     meteor
    -0.68
     conspiracy
    -0.66
    creen
    -0.65
    emouth
    -0.64
     mortg
    -0.63
     minim
    -0.62
    xual
    -0.60
     lunar
    -0.60
     baskets
    -0.59
    POSITIVE LOGITS
    ª
    1.33
    ľ
    1.30
    ¡
    1.27
    Ŀ
    1.16
    ĺ
    1.15
    IJ
    1.12
    ©
    1.11
    Ķ
    1.10
    ł
    1.10
    ¹
    1.08
    Activations Density 0.182%

    No Known Activations