© 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. 6-RES-JB
    11. 19745
    Prev
    Next
    INDEX
    Explanations

    familial relationships, particularly highlighting individuals who are brothers- or sisters-in-law

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships, particularly those defined by marriage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¥ŀ
    -0.72
    izoph
    -0.71
     enthusi
    -0.69
    anche
    -0.68
     enthus
    -0.68
    opian
    -0.67
     acrylic
    -0.66
    OVER
    -0.66
     SOU
    -0.64
    emic
    -0.64
    POSITIVE LOGITS
    yer
    0.96
    yers
    0.93
    hood
    0.79
    ful
    0.77
    ski
    0.74
    lessness
    0.73
    rence
    0.73
    suit
    0.72
    book
    0.71
    ship
    0.71
    Activations Density 0.019%

    No Known Activations