© 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. 4-RES-JB
    11. 6160
    Prev
    Next
    INDEX
    Explanations

    phrases related to discarding or removing something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that involve the concept of removing or getting rid of something

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

    No Comments

    Negative Logits
     Cosponsors
    -0.93
    º
    -0.76
     challeng
    -0.70
    wcs
    -0.70
    ait
    -0.69
    GW
    -0.66
    Rate
    -0.65
    raq
    -0.64
    INC
    -0.63
    NESS
    -0.62
    POSITIVE LOGITS
     pesky
    0.77
     unwanted
    0.74
     stray
    0.74
     virginity
    0.74
     fossil
    0.64
     carc
    0.64
     virgin
    0.64
    olphins
    0.63
     bets
    0.63
     needless
    0.62
    Activations Density 0.071%

    No Known Activations