© 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. 6413
    Prev
    Next
    INDEX
    Explanations

    references to criminal activities or accusations

    oai_token-act-pair · gpt-3.5-turbo

    references to crimes, particularly those associated with humanity and specific offenses committed by individuals or groups

    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
    quickShipAvailable
    -0.80
    achev
    -0.78
    alg
    -0.71
    por
    -0.70
    soDeliveryDate
    -0.68
    ramid
    -0.67
     artificial
    -0.67
    BLIC
    -0.67
     snipp
    -0.65
    agles
    -0.65
    POSITIVE LOGITS
     punishable
    1.20
     committed
    1.20
     perpetrated
    1.05
     spree
    0.99
     involving
    0.94
     offences
    0.94
     crimes
    0.90
     offenses
    0.83
     convictions
    0.82
     against
    0.81
    Activations Density 0.045%

    No Known Activations