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. 16276
    Prev
    Next
    INDEX
    Explanations

    technical terms related to physical devices and operations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to product specifications and technology

    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
    Recent
    -0.74
    reasonable
    -0.74
    borgh
    -0.73
    recent
    -0.73
    ccoli
    -0.72
    ,,,,,,,,
    -0.71
    CRE
    -0.70
    hei
    -0.70
    ometimes
    -0.67
    Large
    -0.66
    POSITIVE LOGITS
     version
    1.63
     portion
    1.53
     counterpart
    1.39
     versions
    1.32
     counterparts
    1.31
     ones
    1.23
     edition
    1.21
     portions
    1.21
     aspect
    1.15
     side
    1.10
    Activations Density 0.387%

    No Known Activations