© 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. 6-RES-JB
    11. 11821
    Prev
    Next
    INDEX
    Explanations

    phrases related to the term "Big"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of significant entities or groups

    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
     confir
    -0.96
    theless
    -0.83
    idency
    -0.79
    istry
    -0.74
    ILA
    -0.69
    anwhile
    -0.69
     livest
    -0.69
     autop
    -0.67
     lawfully
    -0.67
    Dialogue
    -0.67
    POSITIVE LOGITS
    gest
    1.41
    ger
    1.26
    gie
    0.97
    gers
    0.93
    glers
    0.92
    wig
    0.90
    gins
    0.90
    GER
    0.87
    ging
    0.86
    Integer
    0.84
    Activations Density 0.021%

    No Known Activations