© 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. 23454
    Prev
    Next
    INDEX
    Explanations

    numbers representing family members

    oai_token-act-pair · gpt-3.5-turbo

    references to the number of children or family members

    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
    pmwiki
    -0.85
    trial
    -0.73
    ukong
    -0.73
    xtap
    -0.65
    idelines
    -0.65
    fall
    -0.63
    rium
    -0.62
    nown
    -0.61
    TERN
    -0.60
    orius
    -0.60
    POSITIVE LOGITS
     daughters
    0.87
     siblings
    0.76
     sons
    0.75
     boys
    0.74
     generations
    0.70
     grandchildren
    0.70
     kids
    0.70
     Toro
    0.70
     children
    0.69
    thood
    0.69
    Activations Density 0.040%

    No Known Activations