© 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. 418
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "entry"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "entry" levels, particularly in the context of contracts or applications

    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
     opio
    -0.74
     tremend
    -0.67
    illac
    -0.65
    awar
    -0.65
     Band
    -0.63
    cale
    -0.63
     Parables
    -0.62
     Carth
    -0.62
     backdrop
    -0.60
    gans
    -0.59
    POSITIVE LOGITS
    prise
    0.89
    apore
    0.84
    prises
    0.82
    tain
    0.82
     entry
    0.81
    lude
    0.81
    TRY
    0.80
    tainment
    0.79
    prising
    0.77
    vent
    0.74
    Activations Density 0.024%

    No Known Activations