© 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. 2-RES-JB
    11. 24046
    Prev
    Next
    INDEX
    Explanations

    mentions of family members, particularly mothers

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "mom"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.80
    vernment
    -0.74
     Flavoring
    -0.72
    ENGTH
    -0.66
    veyard
    -0.65
    chnology
    -0.65
    IGHTS
    -0.64
    RAFT
    -0.64
     Tribunal
    -0.62
    isson
    -0.61
    POSITIVE LOGITS
    hesis
    1.18
    my
    1.07
    ma
    1.00
     mom
    1.00
    wife
    0.94
     Mom
    0.88
    heses
    0.87
     dad
    0.83
    tor
    0.82
    Mom
    0.82
    Activations Density 0.013%

    No Known Activations