© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 19678
    Prev
    Next
    INDEX
    Explanations

    references to research institutions and activities

    oai_token-act-pair · gpt-3.5-turbo

    references to research organizations and institutions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icago
    -0.67
    âĶĢâĶĢ
    -0.65
     femin
    -0.63
    size
    -0.62
    EMA
    -0.60
    nea
    -0.60
    anza
    -0.59
    ilage
    -0.57
    conv
    -0.57
     gent
    -0.57
    POSITIVE LOGITS
     Associates
    0.87
     Laboratory
    0.83
     Institute
    0.81
     Laboratories
    0.79
     Scientist
    0.79
    edIn
    0.78
    ateur
    0.76
     assistants
    0.76
    Gate
    0.76
     laboratories
    0.75
    Activations Density 0.024%

    No Known Activations