© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 2765
    Prev
    Next
    INDEX
    Explanations

    the concept of guilt or wrongdoing

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "guilty" and its context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edia
    -0.70
    orph
    -0.69
     GP
    -0.66
    artney
    -0.66
    Dub
    -0.65
     Feder
    -0.62
     adoption
    -0.61
    acers
    -0.59
    andel
    -0.59
     wallets
    -0.59
    POSITIVE LOGITS
     guilty
    1.13
     Guilty
    1.08
    thouse
    0.81
     pleas
    0.79
    otine
    0.77
    alty
    0.77
     unfocusedRange
    0.75
     plea
    0.74
    isance
    0.74
     guilt
    0.74
    Activations Density 0.007%

    No Known Activations