© 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. 10-RES-JB
    11. 11614
    Prev
    Next
    INDEX
    Explanations

    instances of the abbreviation "ft" or its variations in text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "ft" as it relates to various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scratch
    -0.71
    pta
    -0.71
    IZE
    -0.68
    gdala
    -0.67
    ggle
    -0.66
    utical
    -0.64
    Ĥİ
    -0.64
    ptives
    -0.63
     Learns
    -0.62
    izational
    -0.61
    POSITIVE LOGITS
    entimes
    1.34
     Punk
    0.98
    hered
    0.91
    raction
    0.87
    ributed
    0.86
    rax
    0.84
    ribute
    0.79
    reet
    0.77
    alion
    0.77
    oday
    0.76
    Activations Density 0.046%

    No Known Activations