© 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. 7-RES-JB
    11. 20603
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically a name 'He' occurring in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "He" used repeatedly in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     guiActiveUnfocused
    -0.65
     +/-
    -0.63
     affiliate
    -0.62
     DSM
    -0.59
     EDITION
    -0.57
     Observer
    -0.55
     AWS
    -0.55
     Veter
    -0.55
     reinforcement
    -0.55
     intrusive
    -0.54
    POSITIVE LOGITS
    zbollah
    1.57
    resy
    1.34
    ldon
    1.23
    gemony
    1.22
    pherd
    1.21
    aven
    1.16
    ather
    1.11
    avier
    1.09
    idi
    1.08
    uristic
    1.04
    Activations Density 0.155%

    No Known Activations