© 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. 7-RES-JB
    11. 13367
    Prev
    Next
    INDEX
    Explanations

    mentions of physical attacks or confrontations

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals involved in violent actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zl
    -0.88
    Balt
    -0.80
    umph
    -0.78
     Revival
    -0.75
     rebirth
    -0.66
     Rebirth
    -0.65
     Chart
    -0.65
    binding
    -0.64
    sit
    -0.64
    urgical
    -0.63
    POSITIVE LOGITS
     attackers
    0.95
     attacker
    0.89
     assailants
    0.87
     gunmen
    0.86
     assailant
    0.80
     attack
    0.80
     beware
    0.79
     intent
    0.79
     wielding
    0.79
     prow
    0.78
    Activations Density 0.076%

    No Known Activations