© 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. 3-RES-JB
    11. 3276
    Prev
    Next
    INDEX
    Explanations

    terms or phrases related to comparison or evaluation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "in terms of"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estern
    -0.76
    ****************
    -0.74
    rote
    -0.74
    resent
    -0.67
    oaded
    -0.66
    oster
    -0.65
     Towns
    -0.65
    riad
    -0.64
    GBT
    -0.64
     tatt
    -0.64
    POSITIVE LOGITS
    cale
    0.96
    pace
    0.90
    eme
    0.90
     guiActiveUn
    0.90
     terms
    0.88
    terms
    0.87
    pheus
    0.85
    paces
    0.80
    forward
    0.78
    flation
    0.77
    Activations Density 0.010%

    No Known Activations