© 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. 11027
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions and observations

    oai_token-act-pair · gpt-3.5-turbo

    affirmative statements and positive actions

    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
     Spons
    -0.82
     sponsoring
    -0.77
    ibrary
    -0.72
     Sources
    -0.68
     Optional
    -0.68
    href
    -0.67
     Sponsor
    -0.66
    soDeliveryDate
    -0.66
     necessity
    -0.66
     Mandatory
    -0.65
    POSITIVE LOGITS
     behaved
    1.38
     deterior
    1.31
     behaves
    1.29
     behave
    1.25
     noticeably
    1.23
     deteriorated
    1.21
     fared
    1.09
     outper
    1.08
     improved
    1.04
     seem
    1.01
    Activations Density 0.391%

    No Known Activations