© 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. 10-RES-JB
    11. 24026
    Prev
    Next
    INDEX
    Explanations

    content related to social media

    oai_token-act-pair · gpt-3.5-turbo

    references to social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nces
    -1.01
    urat
    -0.78
    atche
    -0.76
    _-
    -0.68
    sterdam
    -0.66
     Blazing
    -0.65
     Zup
    -0.64
    1001
    -0.64
    ARDS
    -0.64
    shall
    -0.63
    POSITIVE LOGITS
     networks
    1.15
     networking
    1.13
     media
    1.13
    izing
    0.96
    media
    0.90
    ize
    0.90
     network
    0.88
     platforms
    0.87
    ized
    0.87
    izers
    0.86
    Activations Density 0.022%

    No Known Activations