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. 10-RES-JB
    6. 7518
    Prev
    Next
    INDEX
    Explanations

    phrases related to a nostalgic or retro aesthetic

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of aesthetics and sensations related to style or atmosphere

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     papers
    -0.83
     Articles
    -0.68
    reports
    -0.67
     filib
    -0.64
     paperwork
    -0.63
     cages
    -0.61
     Journals
    -0.60
     textbooks
    -0.60
     PET
    -0.59
     journals
    -0.59
    POSITIVE LOGITS
    iness
    1.06
     reminiscent
    1.04
    ality
    0.98
     perv
    0.98
     vibe
    0.91
     inherent
    0.90
    fulness
    0.88
    smanship
    0.87
     emanating
    0.83
     sprinkled
    0.82
    Activations Density 0.262%

    No Known Activations