INDEX

Explanations

technical instructions or definitions within documents

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

Introductions or clarifications, often with examples

np_acts-logits-general · gemini-2.0-flash

introducing examples or hypotheticals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 оригіналу

-0.69

 تانيه

-0.69

iestety

-0.67

 niestety

-0.63

vrigt

-0.63

 كمان

-0.62

 tevens

-0.61

=$?

-0.61

 atleast

-0.61

 valamint

-0.61

POSITIVE LOGITS

say

1.10

say

0.96

 misalnya

0.95

 bijvoorbeeld

0.90

 Suppose

0.89

 například

0.88

 suppose

0.87

 beispielsweise

0.87

Suppose

0.86

 مث

0.83

Activations Density 0.795%

technical instructions or definitions within documents

Introductions or clarifications, often with examples

introducing examples or hypotheticals

No Comments

No Known Activations