© 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. 1454
    Prev
    Next
    INDEX
    Explanations

    specific mentions of objects with unique visual properties, such as patterns or colors

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "in" and contexts where locations or settings are indicated

    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
     governed
    -0.64
     incumb
    -0.63
    idays
    -0.61
    icides
    -0.61
    MAP
    -0.59
    izophren
    -0.59
     endure
    -0.57
    =]
    -0.57
    Independent
    -0.57
    PASS
    -0.57
    POSITIVE LOGITS
     lieu
    1.26
    clusions
    1.12
     situ
    1.11
     front
    1.02
    ked
    1.01
    sole
    1.00
    between
    0.99
     conjunction
    0.96
    efficiency
    0.95
    activated
    0.92
    Activations Density 0.245%

    No Known Activations