© 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. 7-RES-JB
    11. 2155
    Prev
    Next
    INDEX
    Explanations

    word boundaries within text

    oai_token-act-pair · gpt-3.5-turbo

    character strings or symbols that represent non-standard characters or formatting

    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
     sacrific
    -0.99
     informants
    -0.77
     mathemat
    -0.74
     pyramid
    -0.71
     sock
    -0.69
     advant
    -0.69
     welf
    -0.69
     seiz
    -0.67
     answ
    -0.67
     civilian
    -0.67
    POSITIVE LOGITS
    ï¸ı
    1.22
    iversary
    1.18
    ï¸
    0.89
    winter
    0.88
    resh
    0.85
    when
    0.84
    rough
    0.83
    VERTISEMENT
    0.81
     onwards
    0.80
    ship
    0.78
    Activations Density 0.160%

    No Known Activations