© 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. 7-RES-JB
    11. 24156
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by possessive pronouns or nouns

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns or references to ownership

    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
    lehem
    -0.81
    aunder
    -0.78
    thood
    -0.77
    emp
    -0.76
    Ò
    -0.76
    avis
    -0.75
    obin
    -0.74
    ablishment
    -0.74
    ibaba
    -0.73
    :{
    -0.72
    POSITIVE LOGITS
     own
    1.17
     ancestors
    1.16
     superiors
    1.11
     favourite
    1.07
     inability
    1.04
     predecessors
    1.04
     adversaries
    1.02
     opponents
    1.02
     eldest
    1.01
     beloved
    1.01
    Activations Density 0.221%

    No Known Activations