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

    Neuronpedia

    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. 2-RES-JB
    11. 17103
    Prev
    Next
    INDEX
    Explanations

    references to the ACLU (American Civil Liberties Union)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of civil rights organizations

    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
    lasses
    -0.71
    lass
    -0.69
    fecture
    -0.69
     Camb
    -0.69
    tails
    -0.68
    olls
    -0.67
    prime
    -0.67
    ppo
    -0.65
    cgi
    -0.64
    zzy
    -0.63
    POSITIVE LOGITS
     ACLU
    1.04
     GOODMAN
    0.79
     Fein
    0.74
     Liberties
    0.73
    DEF
    0.72
     Orchestra
    0.72
     Consortium
    0.71
     Machina
    0.70
    OC
    0.70
    Prot
    0.69
    Activations Density 0.005%

    No Known Activations