© 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. 10-RES-JB
    11. 12873
    Prev
    Next
    INDEX
    Explanations

    phrases describing dual roles or functions

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing contrasting dualities or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cies
    -0.83
    zens
    -0.78
    cats
    -0.77
    в
    -0.76
    estyles
    -0.75
    ð
    -0.74
    ICES
    -0.71
    tz
    -0.71
    roups
    -0.71
    ibilities
    -0.69
    POSITIVE LOGITS
     protector
    1.40
     savior
    1.23
     centerpiece
    1.15
     catalyst
    1.14
     confid
    1.12
     facilit
    1.10
     healer
    1.05
     conduit
    1.03
     undermin
    1.01
     scourge
    1.01
    Activations Density 0.240%

    No Known Activations