© 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. 2967
    Prev
    Next
    INDEX
    Explanations

    phrases related to the formation of various entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "formation."

    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
    bor
    -0.72
    ience
    -0.71
    pez
    -0.70
    lems
    -0.70
    consumer
    -0.68
    argo
    -0.67
    ocket
    -0.67
    ahi
    -0.65
    geon
    -0.65
    umbo
    -0.65
    POSITIVE LOGITS
     formation
    1.16
     formations
    1.07
     Formation
    0.98
    idable
    0.94
    eering
    0.88
     forming
    0.81
    aldehyde
    0.77
    formation
    0.76
    forming
    0.74
    ually
    0.73
    Activations Density 0.011%

    No Known Activations