© 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 EvalsExportsinterp-engineNEWAPI 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. 18845
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs indicating intentions or future actions

    oai_token-act-pair · gpt-3.5-turbo

    references to collective experiences or actions involving groups of people

    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
    Reviewer
    -0.80
    REDACTED
    -0.78
     Citation
    -0.76
     Sheen
    -0.67
    ests
    -0.66
    esting
    -0.65
    ipedia
    -0.63
    ¿½
    -0.63
     Examples
    -0.61
     Lyon
    -0.60
    POSITIVE LOGITS
     need
    1.48
    're
    1.41
     NEED
    1.31
    've
    1.30
     haven
    1.30
     couldn
    1.30
     owe
    1.26
    'll
    1.26
     want
    1.24
     intend
    1.23
    Activations Density 0.332%

    No Known Activations