© 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. 8-RES-JB
    11. 17244
    Prev
    Next
    INDEX
    Explanations

    references to specific legal or organizational codes, possibly related to financial or tax matters

    oai_token-act-pair · gpt-3.5-turbo

    references to non-profit organizations and their classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estine
    -0.78
    ock
    -0.72
    robe
    -0.70
    itutes
    -0.70
    lied
    -0.67
    perty
    -0.66
    istic
    -0.66
    izations
    -0.65
    elve
    -0.65
    essen
    -0.65
    POSITIVE LOGITS
     ILCS
    1.08
     SHARES
    0.93
    MHz
    0.90
     MHz
    0.90
    px
    0.85
    °
    0.81
    RF
    0.77
     Squadron
    0.76
    KB
    0.75
     Degree
    0.74
    Activations Density 0.097%

    No Known Activations