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. 11-RES-JB
    6. 18625
    Prev
    Next
    INDEX
    Explanations

    phrases introducing or discussing specific topics or content for brevity

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal expression and choice

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥīãĥ©
    -0.67
    glass
    -0.65
     Pric
    -0.63
     Canaveral
    -0.62
    Amazing
    -0.61
     Appl
    -0.59
    Fax
    -0.59
    HOU
    -0.58
     Colo
    -0.57
     WATCHED
    -0.57
    POSITIVE LOGITS
     suffice
    1.24
     briefly
    1.00
     Suff
    1.00
     spoiler
    0.98
     disclaimer
    0.98
     spoilers
    0.98
     ital
    0.96
     summar
    0.95
     summarize
    0.94
     here
    0.91
    Activations Density 0.416%

    No Known Activations