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. 9-RES-JB
    6. 15078
    Prev
    Next
    INDEX
    Explanations

    terms related to cybersecurity and technical problem-solving

    oai_token-act-pair · gpt-3.5-turbo

    terms related to security testing and web application protection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.88
    oiler
    -0.83
    again
    -0.82
    apo
    -0.78
    amar
    -0.74
    û
    -0.74
    soType
    -0.73
    Gay
    -0.73
     )]
    -0.72
    qqa
    -0.72
    POSITIVE LOGITS
     customized
    1.01
     your
    0.97
     customizable
    0.90
     existing
    0.88
     personalized
    0.87
     custom
    0.84
     clients
    0.82
     automotive
    0.82
     smartphone
    0.82
     smartphones
    0.81
    Activations Density 0.493%

    No Known Activations