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. 7-RES-JB
    6. 17655
    Prev
    Next
    INDEX
    Explanations

    phrases or statements attributing a source of information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the source or origin of information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifix
    -0.85
    itivity
    -0.80
    SPONSORED
    -0.79
    hyde
    -0.74
    ocene
    -0.74
    adian
    -0.72
    itiz
    -0.71
    sic
    -0.71
    seek
    -0.70
    isode
    -0.70
    POSITIVE LOGITS
     afar
    1.12
     whence
    1.04
     thence
    0.83
     Wow
    0.77
     Uni
    0.75
     Above
    0.72
     1967
    0.70
     inception
    0.68
    ources
    0.66
     Carbuncle
    0.65
    Activations Density 0.043%

    No Known Activations