© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 13846
    Prev
    Next
    INDEX
    Explanations

    instances of words related to religious and moral transgressions

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to religious or moral themes, particularly those associated with apostasy and emotional tones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pmwiki
    -0.69
    HCR
    -0.65
     FISA
    -0.64
     numbered
    -0.64
     Caller
    -0.63
     Valent
    -0.62
     Akin
    -0.61
     Reserve
    -0.61
     Settlement
    -0.61
     sights
    -0.61
    POSITIVE LOGITS
    odic
    1.14
    olic
    1.10
    acists
    1.08
    omic
    1.08
    orical
    1.06
    ilit
    1.05
    odes
    1.03
    etically
    1.03
    odied
    1.03
    ol
    1.02
    Activations Density 0.067%

    No Known Activations