© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    6. 19325
    Prev
    Next
    INDEX
    Explanations

    phrases containing variations of the word "drop" and "Drozov"

    oai_token-act-pair · gpt-3.5-turbo

    the word "dro" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Corp
    -0.73
     Woodward
    -0.71
     Amos
    -0.68
    ATIONAL
    -0.67
     Pagan
    -0.67
    Angelo
    -0.67
    UTC
    -0.67
    aya
    -0.66
     Nat
    -0.65
    English
    -0.65
    POSITIVE LOGITS
     dro
    4.16
    dro
    1.92
     Dro
    1.89
     droid
    1.66
    Dro
    1.59
     Droid
    1.34
     aeros
    1.09
     dri
    1.07
     gri
    1.03
     vap
    1.01
    Activations Density 0.020%

    No Known Activations