© 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. 8-RES-JB
    11. 2557
    Prev
    Next
    INDEX
    Explanations

    words related to discussing or reporting on various topics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the topic of "reporting" or discussing various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ¥µ
    -0.86
    pour
    -0.78
    Iterator
    -0.71
    ngth
    -0.69
    andowski
    -0.69
    ieri
    -0.66
    iak
    -0.66
    boot
    -0.65
    appointed
    -0.65
    vertisement
    -0.64
    POSITIVE LOGITS
     topics
    0.98
     oneself
    0.92
     subjects
    0.87
     anything
    0.84
     homosexuality
    0.82
     themselves
    0.82
     Himself
    0.78
     everyday
    0.78
     UFOs
    0.77
     trivial
    0.77
    Activations Density 0.420%

    No Known Activations