© 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. 21443
    Prev
    Next
    INDEX
    Explanations

    positive expressions related to enjoyment or satisfaction

    oai_token-act-pair · gpt-3.5-turbo

    expressions of enjoyment and engagement with content

    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
    quartered
    -0.82
    rugged
    -0.67
    pired
    -0.62
    ospital
    -0.62
    irable
    -0.60
    onna
    -0.59
    overty
    -0.59
    adem
    -0.58
    legates
    -0.58
    interstitial
    -0.57
    POSITIVE LOGITS
     it
    1.14
     :)
    1.14
     ðŁĻĤ
    1.09
     this
    1.05
     everything
    1.04
     accordingly
    1.04
     them
    1.02
     ASAP
    1.01
     ;)
    0.99
     yourselves
    0.98
    Activations Density 0.328%

    No Known Activations