© 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. 7-RES-JB
    6. 11343
    Prev
    Next
    INDEX
    Explanations

    mentions of people's names or titles followed by numbers

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the string "air" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sylv
    -0.76
    ktop
    -0.67
    URES
    -0.65
    enty
    -0.64
    olver
    -0.60
     Ys
    -0.59
     KY
    -0.57
     mov
    -0.56
    endor
    -0.56
    SPONSORED
    -0.56
    POSITIVE LOGITS
    bnb
    1.10
    waves
    1.04
    neau
    1.01
    plane
    0.88
    voy
    0.86
    pin
    0.80
    bestos
    0.79
    oop
    0.79
    cles
    0.78
    cast
    0.78
    Activations Density 0.021%

    No Known Activations