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

    Neuronpedia

    APICircuit 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. 0-RES-JB
    6. 4265
    Prev
    Next
    INDEX
    Explanations

    terms related to encryption and encoding

    oai_token-act-pair · gpt-3.5-turbo

    terms related to encryption and encoding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Louie
    -0.80
     Towns
    -0.76
     Hus
    -0.74
    illary
    -0.72
    ____
    -0.70
     Rush
    -0.68
     benches
    -0.68
    ndra
    -0.67
     Huss
    -0.67
     Ao
    -0.66
    POSITIVE LOGITS
     encrypted
    2.61
    enc
    2.53
     encoding
    2.33
     encrypt
    2.24
    encrypted
    2.22
     encoded
    2.18
     decrypt
    2.18
     encode
    1.99
    Enc
    1.98
     decoding
    1.61
    Activations Density 0.044%

    No Known Activations