© 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. 12751
    Prev
    Next
    INDEX
    Explanations

    positive adjectives or expressions that describe something as impressive or appealing

    oai_token-act-pair · gpt-3.5-turbo

    words indicating positivity or admiration, particularly relating to "cool" and "cute" attributes

    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
    avored
    -0.74
     Inquiry
    -0.71
    emale
    -0.70
    ãĥĺãĥ©
    -0.69
    clair
    -0.68
    ÃŃs
    -0.68
     cautioned
    -0.67
    ustomed
    -0.67
     acutely
    -0.67
     harshly
    -0.64
    POSITIVE LOGITS
     little
    1.17
     stuff
    1.16
     kid
    1.07
     thing
    1.04
    ness
    1.03
    glers
    1.00
     guy
    1.00
     shit
    0.97
     kids
    0.96
     gif
    0.95
    Activations Density 0.109%

    No Known Activations