INDEX

Explanations

specific programming structures or elements in code snippets

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

<start_of_turn>user

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

inSlope

-0.35

 externally

-0.33

quiera

-0.32

 same

-0.31

sihkan

-0.31

 accedi

-0.31

si

-0.30

 arbitrarily

-0.30

༘

-0.29

sur

-0.29

POSITIVE LOGITS

########.

0.87

 informée

0.80

PreferredItem

0.66

uxxxx

0.66

 kasarigan

0.62

 Paglinawan

0.62

Хьажоргаш

0.60

 ویکی‌پدیا

0.59

 Италијани

0.59

 ModelExpression

0.58

Activations Density 0.000%

specific programming structures or elements in code snippets

<start_of_turn>user

No Comments

No Known Activations