© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13924
    Prev
    Next
    INDEX
    Explanations

    references to crime reports with specific details

    oai_token-act-pair · gpt-3.5-turbo

    references to police activity or incidents involving law enforcement

    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
     ageing
    -0.75
     opting
    -0.73
     undermin
    -0.73
     endorsing
    -0.71
     favour
    -0.70
     hed
    -0.69
     scept
    -0.68
     preferring
    -0.67
     renegoti
    -0.66
    odox
    -0.65
    POSITIVE LOGITS
    Authorities
    1.09
    Investigators
    1.09
    Police
    1.00
    Officers
    1.00
     Investigators
    0.85
     Sheriff
    0.84
    Officials
    0.84
     Authorities
    0.84
    Bus
    0.83
    Sym
    0.82
    Activations Density 0.388%

    No Known Activations