© 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. 4-RES-JB
    11. 6850
    Prev
    Next
    INDEX
    Explanations

    specific pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    the repeated use of the word "its" in various contexts

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

    No Comments

    Negative Logits
    tu
    -0.74
     Scully
    -0.68
    Texture
    -0.67
    Bron
    -0.67
    hog
    -0.67
    Show
    -0.67
    Condition
    -0.66
    vere
    -0.66
    AAAA
    -0.66
    picture
    -0.65
    POSITIVE LOGITS
     own
    1.66
     predecessor
    1.14
    ELF
    1.10
     respective
    1.07
     predecessors
    1.05
     namesake
    0.93
     newfound
    0.92
     newest
    0.91
     flagship
    0.90
    self
    0.89
    Activations Density 0.124%

    No Known Activations