© 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. 8-RES-JB
    11. 2683
    Prev
    Next
    INDEX
    Explanations

    words related to violence, brutality, and darkness

    oai_token-act-pair · gpt-3.5-turbo

    references to violence and dark themes in media

    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
     Preferred
    -0.94
    20439
    -0.81
    Companies
    -0.80
     Badge
    -0.79
    Benef
    -0.77
    ITNESS
    -0.77
     Member
    -0.76
    SEA
    -0.76
     Members
    -0.75
     Prosecut
    -0.75
    POSITIVE LOGITS
     realism
    1.49
     tropes
    1.20
     genres
    1.18
     thriller
    1.17
     storytelling
    1.15
     genre
    1.15
     gore
    1.12
     melanch
    1.09
     imagery
    1.09
     poetry
    1.09
    Activations Density 0.425%

    No Known Activations