© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 1850
    Prev
    Next
    INDEX
    Explanations

    words related to enhancing, strengthening, boosting, and increasing

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to improvement and enhancement of conditions or operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mad
    -0.80
    sbm
    -0.77
    rants
    -0.75
    DragonMagazine
    -0.70
     laced
    -0.65
     screamed
    -0.64
    say
    -0.64
     slapped
    -0.64
    coded
    -0.64
     piled
    -0.64
    POSITIVE LOGITS
     productivity
    1.19
     efficiency
    1.15
     awareness
    1.10
     competitiveness
    1.09
     morale
    1.01
     effic
    0.95
     literacy
    0.95
     vitality
    0.94
     prosperity
    0.93
     affordability
    0.93
    Activations Density 0.230%

    No Known Activations