© 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. 9-RES-JB
    11. 15395
    Prev
    Next
    INDEX
    Explanations

    descriptions of interpersonal relationships and ethical dilemmas

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to love and interpersonal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quit
    -0.65
    rez
    -0.55
    ;}
    -0.54
    umbs
    -0.52
    ãĤ´ãĥ³
    -0.52
    BuyableInstoreAndOnline
    -0.52
    akis
    -0.51
    -|
    -0.51
    umbn
    -0.49
    asters
    -0.49
    POSITIVE LOGITS
     moreover
    0.97
     furthermore
    0.94
     secondly
    0.90
     insofar
    0.87
     indeed
    0.83
     consequently
    0.79
     differs
    0.79
     although
    0.76
     specifically
    0.75
     therefore
    0.75
    Activations Density 0.786%

    No Known Activations