© 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. 17310
    Prev
    Next
    INDEX
    Explanations

    phrases related to expressing opinions or emotions strongly

    oai_token-act-pair · gpt-3.5-turbo

    expressions of indifference or disregard

    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
    Ct
    -0.80
    iba
    -0.69
    ById
    -0.68
    eness
    -0.65
    ODY
    -0.64
    yrinth
    -0.63
    ourge
    -0.61
     Jah
    -0.61
    orial
    -0.59
    xtap
    -0.59
    POSITIVE LOGITS
     thumbs
    1.18
     impression
    1.16
     keynote
    0.92
     nod
    0.90
     speeches
    0.87
     shout
    0.83
     hint
    0.83
     indication
    0.79
     cred
    0.76
     rundown
    0.75
    Activations Density 0.131%

    No Known Activations