INDEX

Explanations

repetitive or synonymous phrases and concepts

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

"same"

np_acts-logits-general · gemini-2.0-flash

the same

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RegressionTest

-0.80

 BoxDecoration

-0.72

 jsPsych

-0.64

Jegyzetek

-0.61

 propOrder

-0.59

tomans

-0.57

例句

-0.57

むしろ

-0.56

آباد

-0.55

queryInterface

-0.54

POSITIVE LOGITS

 exact

1.09

 same

1.02

 SAME

0.96

 Same

0.96

Same

0.95

SAME

0.91

same

0.89

isSame

0.86

 thing

0.85

 Exact

0.84

Activations Density 0.119%

repetitive or synonymous phrases and concepts

"same"

the same

No Comments

No Known Activations