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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6192
    Prev
    Next
    INDEX
    Explanations

    pronouns or possessive adjectives related to the third person plural

    oai_token-act-pair · gpt-3.5-turbo

    references to ownership or possession

    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
     Unsure
    -0.78
    Bear
    -0.76
    CCC
    -0.70
    JB
    -0.69
    VI
    -0.69
    AAAA
    -0.68
    scape
    -0.66
    FP
    -0.66
    vine
    -0.66
    zz
    -0.66
    POSITIVE LOGITS
     own
    1.64
     respective
    1.48
    selves
    1.25
     selves
    1.12
    self
    1.05
     newfound
    1.02
     predecessors
    0.99
     namesake
    0.97
     rightful
    0.97
     entire
    0.94
    Activations Density 0.269%

    No Known Activations