© 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. 3909
    Prev
    Next
    INDEX
    Explanations

    references to physical actions related to shoveling

    oai_token-act-pair · gpt-3.5-turbo

    instances of physical labor and actions related to moving materials

    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
    esters
    -0.77
    lus
    -0.74
    ester
    -0.73
    eem
    -0.72
    iosyncr
    -0.71
    onga
    -0.71
    overe
    -0.70
    ioned
    -0.69
    ector
    -0.65
    erve
    -0.64
    POSITIVE LOGITS
     shovel
    1.03
    jamin
    0.77
     mole
    0.77
    ãĥ³ãĤ¸
    0.76
    utical
    0.74
    ãĤ¡
    0.73
    ory
    0.71
     fertil
    0.70
    SHA
    0.69
    ×Ķ
    0.68
    Activations Density 0.030%

    No Known Activations