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. 2-RES-JB
    6. 3479
    Prev
    Next
    INDEX
    Explanations

    mentions of people's belief in a religious figure or ideology

    oai_token-act-pair · gpt-3.5-turbo

    references to belief and disbelief, particularly in a religious context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.75
    Els
    -0.74
     Lovely
    -0.74
     Paste
    -0.71
     Occupations
    -0.67
     Pavilion
    -0.66
     Kardashian
    -0.66
    å¦
    -0.62
    pict
    -0.62
    SIZE
    -0.62
    POSITIVE LOGITS
    ievers
    1.24
    iever
    1.02
     believer
    1.01
    ieving
    1.00
    ieve
    0.99
    fulness
    0.87
     believers
    0.86
    ieved
    0.85
    ieves
    0.84
    atical
    0.82
    Activations Density 0.015%

    No Known Activations