Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 11134
    Prev
    Next
    INDEX
    Explanations

    phrases related to emotions, especially those related to the heart

    oai_token-act-pair · gpt-3.5-turbo

    terms related to emotional experiences and sentiments involving the heart

    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
     disadvant
    -0.74
     newsp
    -0.68
     Altern
    -0.67
     indic
    -0.67
     Princ
    -0.66
     unemploy
    -0.66
    ammy
    -0.66
     Mub
    -0.63
     Sigma
    -0.61
     Shogun
    -0.60
    POSITIVE LOGITS
    strings
    1.32
    warming
    1.07
    felt
    1.03
    rend
    1.02
    broken
    0.98
    ache
    0.92
    enment
    0.88
    burn
    0.84
    plate
    0.84
    hearted
    0.83
    Activations Density 0.023%

    No Known Activations