© 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. 10-RES-JB
    11. 20345
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by a superlative or specific descriptor

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and phrases indicating ownership or personal connection

    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
    umption
    -0.79
    culosis
    -0.79
    ption
    -0.75
    kamp
    -0.71
    anse
    -0.71
    gery
    -0.70
    avery
    -0.70
    matter
    -0.69
    science
    -0.69
    amation
    -0.68
    POSITIVE LOGITS
     favorites
    1.25
     favorite
    1.22
     favourite
    1.17
     favourites
    1.16
     earliest
    1.02
     buddies
    0.98
     predecessors
    0.98
     daughters
    0.98
     informants
    0.98
     own
    0.96
    Activations Density 0.087%

    No Known Activations