© 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. 7628
    Prev
    Next
    INDEX
    Explanations

    the word "fewer" followed by a numerical value

    oai_token-act-pair · gpt-3.5-turbo

    references to decreasing quantities or numbers

    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
    Draft
    -0.73
    wine
    -0.69
    NB
    -0.68
    MO
    -0.67
    Mut
    -0.67
    shire
    -0.66
    agency
    -0.66
    NW
    -0.65
     Immun
    -0.65
    Guard
    -0.64
    POSITIVE LOGITS
     than
    1.27
     Than
    0.89
    than
    0.85
     calories
    0.80
    bies
    0.79
    een
    0.76
     pesky
    0.74
     bells
    0.73
     digits
    0.72
     unwanted
    0.71
    Activations Density 0.021%

    No Known Activations