© 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. 1-RES-JB
    11. 5490
    Prev
    Next
    INDEX
    Explanations

    phrases related to harmony and harmonious concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to harmony and harmonious relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Jackets
    -0.69
    Attempts
    -0.69
    WD
    -0.67
    ³³³³³³³³³³³³³³³³
    -0.63
     Borough
    -0.63
    CVE
    -0.62
    WIN
    -0.62
     Directors
    -0.61
    HY
    -0.60
    BLIC
    -0.60
    POSITIVE LOGITS
     Harmon
    1.25
     harmon
    1.22
    icity
    1.03
     ILCS
    1.01
    ious
    0.99
    iband
    0.96
     harmonic
    0.92
     Harmony
    0.85
    iated
    0.85
    itational
    0.84
    Activations Density 0.009%

    No Known Activations