© 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. 0-RES-JB
    11. 1105
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to agreement or companionship

    oai_token-act-pair · gpt-3.5-turbo

    terms related to guidelines and standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     engine
    -0.66
     order
    -0.66
     chi
    -0.66
     machine
    -0.64
    wheel
    -0.62
     automatic
    -0.59
     readers
    -0.58
     Engine
    -0.58
     unemploy
    -0.57
     charact
    -0.56
    POSITIVE LOGITS
    ides
    4.80
    IDES
    3.04
    ide
    2.77
    ided
    2.37
    iding
    2.30
    IDE
    2.30
    idal
    2.08
    iders
    1.73
    idelines
    1.48
    ids
    1.44
    Activations Density 0.005%

    No Known Activations