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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9-RES-JB
    11. 9168
    Prev
    Next
    INDEX
    Explanations

    quotes and statements within double quotation marks

    oai_token-act-pair · gpt-3.5-turbo

    legal terminology and phrases related to court cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.83
    rosso
    -0.77
     2050
    -0.70
     Millennials
    -0.69
    Europe
    -0.69
    soDeliveryDate
    -0.68
    nect
    -0.68
    introdu
    -0.66
    Adds
    -0.65
     2025
    -0.64
    POSITIVE LOGITS
     Defendant
    1.52
     defendant
    1.37
     Plaintiff
    1.27
     appellant
    1.20
    nsic
    1.19
     Defendants
    1.17
     unlawfully
    1.13
     remorse
    1.12
     manslaughter
    1.12
     allegation
    1.12
    Activations Density 1.000%

    No Known Activations