© 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. 4-RES-JB
    11. 6125
    Prev
    Next
    INDEX
    Explanations

    the term "Sisters" mentioned in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific groups or organizations involved in humanitarian or social causes

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

    No Comments

    Negative Logits
    lasses
    -0.82
    yg
    -0.81
    estamp
    -0.72
    tc
    -0.72
    lass
    -0.69
    ball
    -0.69
    ======
    -0.67
     primitive
    -0.67
    tery
    -0.67
    ather
    -0.66
    POSITIVE LOGITS
    nect
    0.76
     Andromeda
    0.70
    abel
    0.70
    ÃŃn
    0.69
     ç¥ŀ
    0.68
    Ò
    0.68
     Valkyrie
    0.66
     Gaga
    0.66
     Waters
    0.65
    ãĤĤ
    0.64
    Activations Density 0.024%

    No Known Activations