© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 13613
    Prev
    Next
    INDEX
    Explanations

    specific mentions of "your" in relation to computer processes or setups

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns referring to the reader or user

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apo
    -0.84
    ilts
    -0.80
    trak
    -0.74
    oft
    -0.73
    vous
    -0.72
     Originally
    -0.72
    forth
    -0.71
     Goes
    -0.71
     Uriel
    -0.70
     Shapiro
    -0.69
    POSITIVE LOGITS
     own
    1.49
     favourite
    1.12
     favorite
    1.08
    ocard
    1.00
     surroundings
    1.00
     opponent
    0.98
     imagination
    0.95
     fingertips
    0.94
     adversary
    0.92
     desired
    0.90
    Activations Density 0.118%

    No Known Activations