© 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. 8-RES-JB
    11. 22302
    Prev
    Next
    INDEX
    Explanations

    pronouns and descriptors related to physical appearance and personality traits

    oai_token-act-pair · gpt-3.5-turbo

    pronouns referring to male and female characters, indicating the presence and actions of individuals

    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
    Untitled
    -0.81
    earch
    -0.75
    atlantic
    -0.71
    IRE
    -0.71
    committee
    -0.68
    HAM
    -0.65
    wrong
    -0.65
    amaz
    -0.64
    seen
    -0.63
     Horowitz
    -0.63
    POSITIVE LOGITS
     possesses
    1.11
     excel
    1.08
     enjoys
    1.03
     earns
    1.00
     ooz
    1.00
     communicates
    0.99
     thri
    0.99
     emits
    0.98
    'll
    0.95
     rarely
    0.95
    Activations Density 0.395%

    No Known Activations