© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22730
    Prev
    Next
    INDEX
    Explanations

    phrases related to increasing or intensifying actions or situations

    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 @ 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
     Antiqu
    -0.69
    lihood
    -0.69
     Gael
    -0.67
    Interstitial
    -0.66
    KNOWN
    -0.65
    itable
    -0.65
    soever
    -0.65
    ä¸ī
    -0.64
     Comet
    -0.63
    ternity
    -0.62
    POSITIVE LOGITS
     ramp
    1.03
     ramps
    1.00
    aging
    0.96
    inson
    0.87
    het
    0.86
    aroo
    0.85
    hetamine
    0.85
     Ramp
    0.81
    amping
    0.81
    chairs
    0.80
    Activations Density 0.009%

    No Known Activations