© 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. 2-RES-JB
    11. 17038
    Prev
    Next
    INDEX
    Explanations

    instances of specific food-related actions like "chopped"

    oai_token-act-pair · gpt-3.5-turbo

    words related to food preparation or cooking

    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
    stadt
    -0.77
     Fargo
    -0.73
    âĢİ
    -0.67
     Mulcair
    -0.67
    #$
    -0.65
     Fortress
    -0.64
    Wiki
    -0.63
    lander
    -0.63
    hof
    -0.63
    iday
    -0.62
    POSITIVE LOGITS
     planned
    0.66
    lication
    0.63
     emergence
    0.62
     implants
    0.62
    igham
    0.61
     overhe
    0.61
     intended
    0.59
     reinforcement
    0.59
     typical
    0.58
    å£
    0.57
    Activations Density 0.000%

    No Known Activations