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. 8-RES-JB
    6. 8798
    Prev
    Next
    INDEX
    Explanations

    time-related activities or events

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to events and actions taking place in a specific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fundament
    -0.66
    Ħ¢
    -0.66
    Reason
    -0.60
    ":["
    -0.60
     destro
    -0.58
    ĺħ
    -0.57
    """
    -0.57
    Specific
    -0.56
     sacrific
    -0.56
    itives
    -0.55
    POSITIVE LOGITS
     applause
    0.68
    romptu
    0.67
     Thursday
    0.67
     adjourn
    0.65
     microphones
    0.65
     gunfire
    0.65
     Sunday
    0.65
     Friday
    0.65
     Wednesday
    0.65
     Saturday
    0.64
    Activations Density 0.972%

    No Known Activations