© 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. 2-RES-JB
    11. 13374
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of 'condensing'

    oai_token-act-pair · gpt-3.5-turbo

    references to "conditions" or "conditioning" across various contexts

    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
     Skydragon
    -0.83
    chy
    -0.78
     Lans
    -0.78
    tle
    -0.72
     Rivals
    -0.66
    gamer
    -0.65
     Unicorn
    -0.64
    HCR
    -0.63
    kick
    -0.63
    horse
    -0.62
    POSITIVE LOGITS
     cond
    1.23
    ominium
    1.16
    ensation
    1.10
    ensing
    1.05
    enser
    1.04
    ensed
    0.97
    itions
    0.86
    ented
    0.85
    enses
    0.85
    ipers
    0.84
    Activations Density 0.009%

    No Known Activations