INDEX

Explanations

references to previous points or statements made in the text

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

mentioned earlier

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

 vechi

-0.56

 vecchia

-0.52

 legacy

-0.50

 viejos

-0.50

 Subsequent

-0.50

 viejo

-0.50

 actuels

-0.50

 Vergangenheit

-0.49

 vieux

-0.49

 vieille

-0.48

POSITIVE LOGITS

 earlier

1.33

 previously

1.09

Earlier

1.02

earlier

1.02

 Earlier

1.02

 Previously

0.91

 ранее

0.90

 wcześniej

0.89

Previously

0.89

previously

0.87

Activations Density 0.131%

references to previous points or statements made in the text

mentioned earlier

No Comments

No Known Activations