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. 2-RES-JB
    6. 16456
    Prev
    Next
    INDEX
    Explanations

    various mentions of restrictions or limitations

    oai_token-act-pair · gpt-3.5-turbo

    references to restrictions on various freedoms or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rious
    -0.75
    psc
    -0.73
    story
    -0.72
    tein
    -0.69
    past
    -0.69
    sis
    -0.68
    amina
    -0.67
    Local
    -0.66
    aple
    -0.65
    Asia
    -0.64
    POSITIVE LOGITS
     restrictions
    1.22
     restricting
    1.10
     imposed
    1.06
     prohibited
    1.06
     restricts
    0.96
     restriction
    0.96
     prohibiting
    0.91
     infring
    0.91
     barred
    0.89
     prohibitions
    0.88
    Activations Density 0.014%

    No Known Activations