© 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. 8-RES-JB
    11. 21759
    Prev
    Next
    INDEX
    Explanations

    mentions of specific pronouns followed by verbs in past or present tense

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "He" in varying contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cubic
    -0.65
    Reviewer
    -0.64
     totality
    -0.59
    Bound
    -0.59
     possession
    -0.58
    amazon
    -0.58
    ÙĦ
    -0.58
    ãĤ¤
    -0.57
     guiActiveUnfocused
    -0.57
     Marketable
    -0.57
    POSITIVE LOGITS
    zbollah
    1.22
    resy
    1.11
     added
    1.03
     cites
    1.02
     likened
    1.00
    zek
    0.98
    'd
    0.97
     believes
    0.97
    idi
    0.97
     cautioned
    0.97
    Activations Density 0.193%

    No Known Activations