© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 7104
    Prev
    Next
    INDEX
    Explanations

    numerical values preceded by "ago"

    oai_token-act-pair · gpt-3.5-turbo

    the frequency of the word "ago" in various contexts

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

    No Comments

    Negative Logits
     mathemat
    -0.86
     suspic
    -0.78
     plaus
    -0.76
     glim
    -0.72
     uniqueness
    -0.71
     simultaneous
    -0.69
     illumination
    -0.67
     tremend
    -0.67
     intuitive
    -0.66
     mobility
    -0.66
    POSITIVE LOGITS
    vernment
    1.40
    zzi
    1.05
    zzo
    0.99
    etta
    0.95
    onga
    0.95
    ago
    0.91
    xon
    0.91
    allo
    0.87
    asca
    0.87
     Mata
    0.87
    Activations Density 0.007%

    No Known Activations