© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 15290
    Prev
    Next
    INDEX
    Explanations

    religious and philosophical sentiments

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to messages and deeper meanings

    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
    Specifically
    -0.75
     respondents
    -0.68
    RM
    -0.67
     commenters
    -0.66
    Article
    -0.66
    Executive
    -0.65
    umably
    -0.65
    Based
    -0.65
    Basically
    -0.65
     commenter
    -0.64
    POSITIVE LOGITS
     everlasting
    0.97
     eternity
    0.97
     darkness
    0.93
     sorrow
    0.92
     longing
    0.91
     souls
    0.91
     solitude
    0.90
     eternal
    0.90
     lonely
    0.90
     faint
    0.89
    Activations Density 1.298%

    No Known Activations