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. 8-RES-JB
    6. 22749
    Prev
    Next
    INDEX
    Explanations

    safety tips and instructions

    oai_token-act-pair · gpt-3.5-turbo

    instructions or advice related to safety and preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    john
    -0.71
    ylan
    -0.66
     descendants
    -0.65
    Today
    -0.63
    ocaust
    -0.63
    upon
    -0.62
     Founder
    -0.62
     vanished
    -0.61
    "}
    -0.60
     purportedly
    -0.60
    POSITIVE LOGITS
     yourself
    1.07
     yourselves
    0.90
     carefully
    0.86
     beforehand
    0.86
     consistency
    0.86
     Yourself
    0.85
     spacing
    0.83
     minimize
    0.81
     wisely
    0.80
     spaced
    0.79
    Activations Density 0.722%

    No Known Activations