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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2-RES-JB
    11. 15360
    Prev
    Next
    INDEX
    Explanations

    phrases related to criminal activities and law enforcement

    oai_token-act-pair · gpt-3.5-turbo

    words related to accomplices and victims in a crime context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     daylight
    -0.72
    anga
    -0.67
    imeter
    -0.66
    utterstock
    -0.64
    ROM
    -0.63
     sunlight
    -0.62
    aber
    -0.61
     rain
    -0.61
     precipitation
    -0.60
     SPR
    -0.59
    POSITIVE LOGITS
    ele
    0.79
    volent
    0.76
     Ethiop
    0.74
    hood
    0.72
    esses
    0.70
    folk
    0.70
     Serge
    0.68
    doms
    0.68
     helpers
    0.67
    fare
    0.65
    Activations Density 0.121%

    No Known Activations