© 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. 7838
    Prev
    Next
    INDEX
    Explanations

    words related to technology companies or products

    oai_token-act-pair · gpt-3.5-turbo

    words or terms related to specific entities and their actions or attributes

    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
    hovah
    -0.74
     Seym
    -0.72
    eworthy
    -0.72
    ordering
    -0.71
    ipeg
    -0.65
    ichick
    -0.64
    accompan
    -0.64
    sticks
    -0.64
    azaki
    -0.63
    erest
    -0.63
    POSITIVE LOGITS
     Lauder
    0.95
    ibles
    0.70
    xual
    0.67
     Polo
    0.64
     Athletics
    0.64
    osterone
    0.63
    ema
    0.63
    uration
    0.63
    å°Ĩ
    0.62
    èĢħ
    0.62
    Activations Density 0.479%

    No Known Activations