© 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. 6088
    Prev
    Next
    INDEX
    Explanations

    times and locations related to police incidents

    oai_token-act-pair · gpt-3.5-turbo

    time-related details and emergency response incidents

    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
     divest
    -0.65
     dissent
    -0.63
     sleeve
    -0.62
     GIF
    -0.61
     reprint
    -0.61
     bios
    -0.60
     dearly
    -0.60
    osponsors
    -0.60
     blink
    -0.60
     Fate
    -0.59
    POSITIVE LOGITS
     EDT
    0.97
     CST
    0.92
     curfew
    0.86
     EST
    0.83
     PDT
    0.82
    .,
    0.82
     PST
    0.81
    âĸĪâĸĪ
    0.79
     gunshots
    0.79
    threatening
    0.76
    Activations Density 0.084%

    No Known Activations