© 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. 6-RES-JB
    11. 9872
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal charges and legal actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "charged" in relation to criminal activity

    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
    DragonMagazine
    -0.94
    Tokens
    -0.81
    TPPStreamerBot
    -0.80
    clips
    -0.78
    ats
    -0.71
    hops
    -0.71
    bytes
    -0.70
    nes
    -0.69
    Sport
    -0.67
    hens
    -0.65
    POSITIVE LOGITS
     felony
    1.07
     misdemeanor
    0.98
    orney
    0.87
     misdem
    0.84
    holding
    0.81
     treason
    0.79
     manslaughter
    0.76
     criminal
    0.76
     convict
    0.74
     maintaining
    0.73
    Activations Density 0.034%

    No Known Activations