© 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. 10-RES-JB
    11. 12884
    Prev
    Next
    INDEX
    Explanations

    phrases related to political statements or calls for action

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration and demands for change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sighting
    -0.74
     alert
    -0.72
     optionally
    -0.69
    erning
    -0.67
     sensing
    -0.67
     fluent
    -0.66
    spring
    -0.65
     intrigued
    -0.65
     sensations
    -0.65
    theless
    -0.64
    POSITIVE LOGITS
     wasteful
    1.46
     irresponsible
    1.20
     greed
    1.18
     inequ
    1.16
     unsustainable
    1.13
     unjust
    1.11
     injustice
    1.11
     bloated
    1.09
     inefficient
    1.09
     senseless
    1.07
    Activations Density 0.899%

    No Known Activations