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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 13560
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate actions or instructions related to personal engagement or communication

    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
    Contin
    -0.74
    AX
    -0.71
    cium
    -0.68
    ãĥĹ
    -0.65
    iband
    -0.62
    oids
    -0.61
    enium
    -0.61
    iber
    -0.60
    GO
    -0.60
    ibu
    -0.60
    POSITIVE LOGITS
     theirs
    1.85
     hers
    1.64
     yours
    1.59
     ours
    1.55
     mine
    1.40
     your
    1.26
     my
    1.22
     his
    1.19
    your
    1.18
     YOUR
    1.16
    Activations Density 0.405%

    No Known Activations