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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1-RES-JB
    6. 14891
    Prev
    Next
    INDEX
    Explanations

    mentions of the organization "Muslim Brotherhood."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Brotherhood" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Glasgow
    -0.81
    kj
    -0.72
    Graham
    -0.71
    ````
    -0.70
    ITIES
    -0.70
    acly
    -0.68
    Lew
    -0.68
    erry
    -0.67
    ties
    -0.66
    ++++++++++++++++
    -0.66
    POSITIVE LOGITS
     Brotherhood
    1.27
    ollah
    0.89
    rats
    0.80
    heit
    0.76
    thren
    0.75
     affili
    0.72
    alions
    0.72
     infiltr
    0.71
     informants
    0.70
     operatives
    0.70
    Activations Density 0.009%

    No Known Activations