© 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. 8-RES-JB
    6. 20474
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing thoughts or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the letter "d" in various contexts

    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
     PSP
    -0.60
     combustion
    -0.60
     behaviours
    -0.59
     Sleeping
    -0.57
     Household
    -0.56
     Verge
    -0.56
     reperto
    -0.56
     deployments
    -0.56
     Prepar
    -0.56
     executions
    -0.55
    POSITIVE LOGITS
    ividual
    1.33
    iversity
    1.01
    rew
    0.98
    yssey
    0.96
    apest
    0.88
    icate
    0.86
    agree
    0.84
    iscover
    0.84
    avis
    0.83
    iamond
    0.83
    Activations Density 0.017%

    No Known Activations