© 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. 9-RES-JB
    11. 16411
    Prev
    Next
    INDEX
    Explanations

    phrases related to police or emergency situations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern about safety and community issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.72
    ortium
    -0.70
    Indeed
    -0.70
    ãĤ´ãĥ³
    -0.67
    ãĢij
    -0.67
     Alas
    -0.66
     revised
    -0.66
    successfully
    -0.65
    *:
    -0.65
    使
    -0.64
    POSITIVE LOGITS
     somebody
    0.96
    ,'"
    0.91
     vandalism
    0.87
     robberies
    0.83
     everybody
    0.82
     scares
    0.81
     burgl
    0.80
     kids
    0.80
     neighbors
    0.80
     tourists
    0.80
    Activations Density 0.776%

    No Known Activations