© 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. 11-RES-JB
    6. 21459
    Prev
    Next
    INDEX
    Explanations

    numbers and percentages

    oai_token-act-pair · gpt-3.5-turbo

    discussions about current societal issues and implications

    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
     ?)
    -0.78
    )\
    -0.78
    ?),
    -0.73
    come
    -0.70
    ?ãĢį
    -0.69
    utterstock
    -0.66
    )+
    -0.65
    adj
    -0.65
    apest
    -0.65
    )?
    -0.64
    POSITIVE LOGITS
    senal
    0.83
     Palestin
    0.68
     mathemat
    0.65
     robotics
    0.63
     chirop
    0.63
     pestic
    0.61
    .
    0.61
     philosophers
    0.60
     RPGs
    0.60
     homebrew
    0.60
    Activations Density 0.698%

    No Known Activations