© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 7892
    Prev
    Next
    INDEX
    Explanations

    mentions of social media

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media

    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
    nces
    -0.98
    ilts
    -0.74
    urat
    -0.73
     Cursed
    -0.72
    shall
    -0.72
    xual
    -0.71
    atche
    -0.70
    ARDS
    -0.67
     Flore
    -0.64
     Ridge
    -0.64
    POSITIVE LOGITS
     networks
    1.01
     networking
    0.98
    izing
    0.90
     gatherings
    0.83
     media
    0.83
    istic
    0.81
    ized
    0.80
    isms
    0.79
     cues
    0.78
     platforms
    0.78
    Activations Density 0.027%

    No Known Activations