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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 7-RES-JB
    6. 2346
    Prev
    Next
    INDEX
    Explanations

    discussions related to freedom of expression

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of freedom, particularly freedom of expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eor
    -0.80
    ergy
    -0.78
    ents
    -0.74
    mers
    -0.72
    itated
    -0.71
    ded
    -0.71
    ENTS
    -0.70
    liam
    -0.69
     Dynasty
    -0.67
    senal
    -0.67
    POSITIVE LOGITS
    bies
    0.90
     roam
    0.90
     guaranteed
    0.85
     freedoms
    0.77
     Fighters
    0.77
     freedom
    0.76
    boot
    0.76
    freedom
    0.75
     afforded
    0.74
     unrestricted
    0.73
    Activations Density 0.023%

    No Known Activations