© 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. 2-RES-JB
    11. 23620
    Prev
    Next
    INDEX
    Explanations

    phrases related to increasing or intensifying actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ramp" and its variations

    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
    lihood
    -0.75
    itable
    -0.67
     Antiqu
    -0.67
    MET
    -0.66
     Manny
    -0.66
    çĭ
    -0.66
     Gael
    -0.65
     Comet
    -0.64
    hiro
    -0.63
     Doctrine
    -0.62
    POSITIVE LOGITS
     ramp
    1.14
     ramps
    1.03
    inson
    0.95
    aging
    0.90
    aroo
    0.88
     Ramp
    0.86
    chairs
    0.83
    het
    0.82
    hetamine
    0.82
    aign
    0.81
    Activations Density 0.005%

    No Known Activations