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

    Neuronpedia

    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. 10-RES-JB
    11. 13841
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by some form of the verb "mean."

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating personal perspective or opinion

    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
     unsolved
    -0.84
    gettable
    -0.80
    uries
    -0.72
    Reviewer
    -0.69
    itaire
    -0.68
    rontal
    -0.64
     srfAttach
    -0.64
     addictive
    -0.62
     summers
    -0.61
    efeated
    -0.60
    POSITIVE LOGITS
     referring
    1.58
     meant
    1.42
     implying
    1.37
     mean
    1.35
     imply
    1.30
     referencing
    1.24
     refers
    1.24
     refer
    1.15
     quoting
    1.12
     means
    1.08
    Activations Density 0.381%

    No Known Activations