Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 18618
    Prev
    Next
    INDEX
    Explanations

    words and acronyms related to countries and international organizations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the string "om"

    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
    Wr
    -0.69
    LIST
    -0.67
     Actual
    -0.66
    VICE
    -0.64
     nexus
    -0.62
    VO
    -0.61
     overpower
    -0.60
    ++++++++++++++++
    -0.60
    lift
    -0.59
     compuls
    -0.58
    POSITIVE LOGITS
    obile
    1.25
    otive
    1.21
    puter
    1.15
    obiles
    1.15
    edia
    1.13
    agnetic
    1.10
    atoes
    1.09
    pson
    1.07
    orrow
    1.03
    merce
    1.03
    Activations Density 0.033%

    No Known Activations