© 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. 12931
    Prev
    Next
    INDEX
    Explanations

    terms related to editing or changes within a text

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "red."

    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
    OHN
    -0.71
    OTOS
    -0.65
    oteric
    -0.63
    ··
    -0.63
    SPONSORED
    -0.63
    renheit
    -0.62
    Story
    -0.61
    ISTORY
    -0.59
    MF
    -0.59
    ZI
    -0.59
    POSITIVE LOGITS
    uced
    1.13
    uces
    1.11
    irect
    1.08
    acted
    1.06
    der
    1.05
    emption
    0.99
    ucing
    0.99
    cliffe
    0.98
    ragon
    0.97
    ding
    0.96
    Activations Density 0.011%

    No Known Activations