© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    6. 17514
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by a verb indicating permission or action, such as "allow them" or "let me."

    oai_token-act-pair · gpt-3.5-turbo

    references to personal or collective empowerment and control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    igil
    -0.62
    ãĥĻ
    -0.60
    Sax
    -0.60
    erno
    -0.59
    UF
    -0.59
    requires
    -0.57
    Issue
    -0.56
    doi
    -0.56
    govtrack
    -0.55
    entric
    -0.55
    POSITIVE LOGITS
     access
    1.02
     unrestricted
    0.96
     flexibility
    0.93
     unlimited
    0.91
     to
    0.89
     freely
    0.78
     limitless
    0.76
     freedom
    0.74
     ample
    0.73
     peek
    0.70
    Activations Density 0.164%

    No Known Activations