© 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. 0-RES-JB
    11. 6377
    Prev
    Next
    INDEX
    Explanations

    words related to moral concepts, particularly focusing on the concept of 'moral.'

    oai_token-act-pair · gpt-3.5-turbo

    references to moral or ethical topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     clock
    -0.76
     jugg
    -0.74
     wi
    -0.69
     fuzz
    -0.69
     nowhere
    -0.67
     fuse
    -0.67
     amps
    -0.63
     piles
    -0.63
     cat
    -0.62
     Cat
    -0.61
    POSITIVE LOGITS
    oral
    4.80
    orial
    1.42
    oric
    1.38
    orate
    1.29
    ora
    1.21
    moral
    1.19
    orical
    1.14
    ors
    1.11
    ental
    1.11
    ori
    1.10
    Activations Density 0.018%

    No Known Activations