© 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. 17722
    Prev
    Next
    INDEX
    Explanations

    mentions of negative events or allegations

    oai_token-act-pair · gpt-3.5-turbo

    dialogue or quotes from various speakers in a text

    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
    ¬¼
    -0.82
    ²¾
    -0.80
    ħĭ
    -0.80
    etheless
    -0.79
    ĻĤ
    -0.69
    anmar
    -0.69
    ©¶æ
    -0.68
    ļéĨĴ
    -0.65
    ĪĴ
    -0.64
    Ĭ
    -0.63
    POSITIVE LOGITS
     writes
    1.28
     wrote
    1.22
     reads
    1.18
     explains
    1.13
     recalls
    1.12
     according
    1.05
     says
    1.05
     recalled
    1.05
     observes
    1.04
     explained
    1.03
    Activations Density 0.101%

    No Known Activations