© 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. 16688
    Prev
    Next
    INDEX
    Explanations

    words related to critiques or negative aspects

    oai_token-act-pair · gpt-3.5-turbo

    references to danger or risk

    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
    ilus
    -0.76
    orsi
    -0.69
    utz
    -0.68
    Critical
    -0.68
     Incre
    -0.67
    idental
    -0.67
    ¿½
    -0.67
    goal
    -0.66
    matic
    -0.65
    etta
    -0.64
    POSITIVE LOGITS
     spacious
    0.95
     hosp
    0.94
     bustling
    0.89
     maze
    0.88
     stocked
    0.85
     deserted
    0.84
     labyrinth
    0.82
     amenities
    0.82
     crowded
    0.81
     sparse
    0.80
    Activations Density 1.101%

    No Known Activations