© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 18309
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "fourth" preceded by either ordinal numbers or one of the forms of the word "four."

    oai_token-act-pair · gpt-3.5-turbo

    the term "fourth."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Petraeus
    -0.73
    UTION
    -0.69
     Mahm
    -0.69
    Statistics
    -0.64
    facts
    -0.64
    Boost
    -0.63
    ETS
    -0.62
    builders
    -0.61
     Lerner
    -0.61
    NUM
    -0.60
    POSITIVE LOGITS
    teenth
    1.21
    ieth
    1.00
     inning
    0.96
    irty
    0.92
    ority
    0.91
     baseman
    0.82
    teen
    0.81
     installment
    0.80
    uous
    0.78
    assian
    0.78
    Activations Density 0.023%

    No Known Activations