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. 6-RES-JB
    6. 19925
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships between individuals or groups, especially in political contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anova
    -0.81
    emonium
    -0.75
    Iterator
    -0.75
    NB
    -0.74
    atoon
    -0.74
    bet
    -0.69
    ciation
    -0.68
    brainer
    -0.67
    lins
    -0.65
    hari
    -0.65
    POSITIVE LOGITS
     aforementioned
    1.03
     Clintons
    1.01
     latter
    0.98
     nascent
    0.93
     nation
    0.92
    ocratic
    0.89
     country
    0.88
     burgeoning
    0.88
     environment
    0.87
     upcoming
    0.86
    Activations Density 0.537%

    No Known Activations