© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 18524
    Prev
    Next
    INDEX
    Explanations

    words related to a specific person's name, potentially used in news articles or other content

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals with the last name 'annon.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    changes
    -0.78
    ©¶æ
    -0.75
    century
    -0.69
    ahime
    -0.68
    venge
    -0.68
    æĸ¹
    -0.68
    demand
    -0.68
    through
    -0.66
    graded
    -0.66
     mortals
    -0.65
    POSITIVE LOGITS
    annon
    1.05
    inational
    0.76
    sburg
    0.76
    ageddon
    0.75
    abin
    0.75
    ieri
    0.74
    cia
    0.74
    ificent
    0.73
    eton
    0.72
    ball
    0.72
    Activations Density 0.006%

    No Known Activations