© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 22033
    Prev
    Next
    INDEX
    Explanations

    words related to a specific focus or center

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with centricity and focus in various contexts, particularly emphasizing perspectives or biases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    externalActionCode
    -0.76
    åĤ
    -0.70
    hand
    -0.67
     Continued
    -0.65
    ãģį
    -0.62
    hner
    -0.61
    cell
    -0.61
    ohan
    -0.61
    leaf
    -0.60
    ICH
    -0.59
    POSITIVE LOGITS
    entric
    0.91
    centric
    0.90
    antry
    0.78
    acies
    0.78
    cycles
    0.78
    ity
    0.75
    nesday
    0.73
    rals
    0.72
    minist
    0.71
     revolving
    0.70
    Activations Density 0.008%

    No Known Activations