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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6-RES-JB
    6. 14041
    Prev
    Next
    INDEX
    Explanations

    phrases containing variations of the word "untethered."

    oai_token-act-pair · gpt-3.5-turbo

    suffixes that denote various forms of taxation or regulatory terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inus
    -0.68
     Carnage
    -0.67
    aan
    -0.65
    HAEL
    -0.65
     Industry
    -0.64
     Soda
    -0.64
     Peterson
    -0.64
    erva
    -0.63
     Punk
    -0.63
     Tate
    -0.62
    POSITIVE LOGITS
    ledged
    1.08
    ishable
    1.03
    able
    0.94
    vable
    0.91
    iable
    0.88
    ables
    0.88
    ministic
    0.85
    oppable
    0.80
    bered
    0.79
    ifiable
    0.78
    Activations Density 0.058%

    No Known Activations