© 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. 11-RES-JB
    11. 12460
    Prev
    Next
    INDEX
    Explanations

    words related to socio-political issues and economic concerns

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to societal challenges and needs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -1.08
    ĸļ
    -0.75
    utenberg
    -0.75
    ãĥ¯ãĥ³
    -0.74
    apsed
    -0.73
    ãĥĩãĤ£
    -0.72
    eanor
    -0.70
    VERTISEMENT
    -0.70
    ahime
    -0.70
    ounding
    -0.70
    POSITIVE LOGITS
     they
    0.99
    they
    0.91
     rapists
    0.91
     husbands
    0.86
     forbid
    0.84
     THEY
    0.84
     capitalists
    0.84
     hospitals
    0.84
     promote
    0.83
     regulate
    0.82
    Activations Density 0.555%

    No Known Activations