© 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. 8-RES-JB
    11. 4619
    Prev
    Next
    INDEX
    Explanations

    phrases related to putting skills to use

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the act of utilizing or putting something to use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oslov
    -0.68
     implicated
    -0.61
    ida
    -0.59
    interstitial
    -0.57
     Establishment
    -0.56
    DI
    -0.55
     Emerging
    -0.55
     RELE
    -0.54
     dist
    -0.54
    scl
    -0.54
    POSITIVE LOGITS
    ggles
    1.02
    pless
    0.87
    asting
    0.83
    wered
    0.81
    perty
    0.80
    lling
    0.78
    asted
    0.75
    lled
    0.74
    psy
    0.73
     rout
    0.70
    Activations Density 0.097%

    No Known Activations