Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15238
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a decision or consequence

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases indicating potential risks or consequences

    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
    emouth
    -0.78
    OST
    -0.72
    owered
    -0.71
    ascus
    -0.67
    resents
    -0.66
    essential
    -0.66
    uded
    -0.65
    keyes
    -0.64
    IME
    -0.63
    uner
    -0.63
    POSITIVE LOGITS
     else
    1.69
    Else
    1.20
     perish
    1.18
     risk
    1.11
     starve
    1.05
     suffer
    1.05
     alternatively
    1.03
     forfeit
    0.99
     worse
    0.98
     die
    0.96
    Activations Density 0.120%

    No Known Activations