© 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. 3-RES-JB
    11. 4319
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and possessive pronouns referring to the speaker or other people

    oai_token-act-pair · gpt-3.5-turbo

    references to the speaker or the speaker's perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    1945
    -0.70
    REP
    -0.60
    Generic
    -0.59
    Rand
    -0.58
    realDonaldTrump
    -0.58
    ORN
    -0.56
    York
    -0.56
    ENE
    -0.55
    ingen
    -0.55
    Phase
    -0.54
    POSITIVE LOGITS
    idd
    0.68
    adows
    0.67
    asure
    0.67
    cknowled
    0.67
    adow
    0.67
    orah
    0.66
    asuring
    0.66
    sted
    0.65
    pher
    0.65
    anwhile
    0.63
    Activations Density 0.139%

    No Known Activations