© 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. 6-RES-JB
    11. 7680
    Prev
    Next
    INDEX
    Explanations

    phrases related to the external appearance or location of objects

    oai_token-act-pair · gpt-3.5-turbo

    references to the concepts of "inside" and "outside."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iji
    -1.04
    enegger
    -0.81
    arcity
    -0.78
    thumbnails
    -0.75
    ute
    -0.75
    lda
    -0.74
    illed
    -0.73
    Corp
    -0.70
    wo
    -0.70
     Rampage
    -0.70
    POSITIVE LOGITS
     workings
    0.81
     underside
    0.75
    most
    0.74
     track
    0.71
     panel
    0.70
     wing
    0.70
     diameter
    0.70
     observer
    0.68
     casing
    0.67
     flap
    0.67
    Activations Density 0.053%

    No Known Activations