© 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. 6-RES-JB
    11. 14960
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate actions or intentions, often starting with "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.88
     Compass
    -0.72
    DOWN
    -0.68
    Dash
    -0.67
     Snap
    -0.66
    eyes
    -0.66
     Crate
    -0.64
    ese
    -0.62
    Enlarge
    -0.62
     minds
    -0.61
    POSITIVE LOGITS
     achieve
    0.89
     dismantle
    0.89
    pless
    0.81
     accumulate
    0.80
    ãĥ¼ãĥĨ
    0.79
     fulfill
    0.78
     become
    0.78
    ãĥ¼ãĥĨãĤ£
    0.77
    姫
    0.75
     accomplish
    0.74
    Activations Density 0.042%

    No Known Activations