INDEX

Explanations

expressions of personal reflections and philosophical insights

oai_token-act-pair · gpt-4o-mini Triggered by @bot

quoting sayings and explanations

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

msgTypes

-0.59

ագրություններ

-0.55

 հղումներ

-0.54

]")]

-0.54

Aiheesta

-0.54

 linkovi

-0.52

Hochspringen

-0.51

 otomatig

-0.50

ureusement

-0.49

 kohdetta

-0.49

POSITIVE LOGITS

 paraph

0.84

这句话

0.84

 quoted

0.77

 paraphrase

0.77

 quote

0.72

 echoed

0.72

 interpreted

0.70

 quoting

0.66

Quote

0.66

 meaning

0.62

Activations Density 0.081%

expressions of personal reflections and philosophical insights

quoting sayings and explanations

No Comments

No Known Activations