© 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. 6-RES-JB
    6. 11772
    Prev
    Next
    INDEX
    Explanations

    information related to financial statistics and percentages

    oai_token-act-pair · gpt-3.5-turbo

    references to specific demographic groups or entities in statistical contexts

    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
    RAW
    -0.68
    odox
    -0.67
    ãĤ´ãĥ³
    -0.66
    ãĥ¥
    -0.66
    ollah
    -0.65
    asso
    -0.65
     impunity
    -0.65
     Skinner
    -0.65
    apego
    -0.63
     Houth
    -0.61
    POSITIVE LOGITS
     surveyed
    1.08
     polled
    1.08
     respondents
    0.79
     nationwide
    0.75
     households
    0.70
    ength
    0.70
     âĶľ
    0.69
    ngth
    0.69
    Minimum
    0.69
     earners
    0.68
    Activations Density 0.160%

    No Known Activations