© 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. 7-RES-JB
    11. 23121
    Prev
    Next
    INDEX
    Explanations

    phrases related to advocating or arguing for a particular position or viewpoint

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to making arguments or presenting cases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seym
    -0.69
     outage
    -0.67
    ummer
    -0.66
     Territories
    -0.64
    ãĥĺ
    -0.64
     Dresden
    -0.64
    onder
    -0.62
    kered
    -0.62
     typo
    -0.59
     ILCS
    -0.58
    POSITIVE LOGITS
     why
    0.88
    Against
    0.85
     against
    0.81
     convinc
    0.79
    against
    0.79
    aneers
    0.75
     persuasive
    0.73
     compelling
    0.71
    agine
    0.70
     arguments
    0.70
    Activations Density 0.069%

    No Known Activations