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. 8-RES-JB
    6. 19576
    Prev
    Next
    INDEX
    Explanations

    mentions of violent activities resulting in harm or death

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with violent incidents or deaths

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -0.65
     devs
    -0.63
    TeX
    -0.60
    */(
    -0.60
    Ability
    -0.59
     accordingly
    -0.57
    pmwiki
    -0.57
    ":"/
    -0.57
     chars
    -0.56
    english
    -0.56
    POSITIVE LOGITS
     robbery
    0.83
     brutally
    0.82
     estranged
    0.82
     murdered
    0.81
     fatally
    0.81
     murder
    0.81
     abducted
    0.80
     abduction
    0.79
     raped
    0.78
     homicide
    0.77
    Activations Density 1.053%

    No Known Activations