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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 12731
    Prev
    Next
    INDEX
    Explanations

    the term "latest."

    oai_token-act-pair · gpt-3.5-turbo

    references to current news and updates

    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
    shared
    -0.81
    umbing
    -0.79
    hovah
    -0.79
    xual
    -0.78
    alties
    -0.78
    wright
    -0.77
    dinand
    -0.76
    ifference
    -0.75
    erved
    -0.72
    ribed
    -0.71
    POSITIVE LOGITS
     incarnation
    1.10
     developments
    0.97
     iteration
    0.93
     edition
    0.92
     installment
    0.89
     update
    0.87
     updates
    0.86
     arrivals
    0.84
     version
    0.84
    Versions
    0.77
    Activations Density 0.033%

    No Known Activations