© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 12136
    Prev
    Next
    INDEX
    Explanations

    the word "Gi" followed by a single-digit number, possibly indicating a specific reference or entity

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Giordano."

    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
    */(
    -0.80
    ioned
    -0.78
    icative
    -0.75
    tenance
    -0.75
    stage
    -0.74
    nesday
    -0.74
    orative
    -0.74
    suit
    -0.71
    imity
    -0.70
     Hots
    -0.70
    POSITIVE LOGITS
    Gi
    0.98
    TeX
    0.92
    vernment
    0.90
    ugal
    0.87
    qs
    0.87
    elin
    0.86
    orno
    0.85
    olla
    0.82
    ugi
    0.82
    etta
    0.81
    Activations Density 0.019%

    No Known Activations