© 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. 9-RES-JB
    11. 1012
    Prev
    Next
    INDEX
    Explanations

    violent actions or events, such as attacking, arresting, or shooting

    oai_token-act-pair · gpt-3.5-turbo

    actions and events related to physical altercations or confrontations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soDeliveryDate
    -0.85
    ackets
    -0.75
    Maps
    -0.74
     maps
    -0.71
     treaties
    -0.70
    Thumbnail
    -0.68
     stadiums
    -0.68
     albums
    -0.67
    ometers
    -0.66
    ©¶æ
    -0.66
    POSITIVE LOGITS
     assailant
    1.10
     perpetrator
    1.09
     attacker
    1.02
     person
    1.01
     intruder
    0.99
     guy
    0.97
     victim
    0.94
     occupant
    0.92
     Someone
    0.92
    someone
    0.87
    Activations Density 0.782%

    No Known Activations