INDEX

Explanations

terms related to comparison and similarity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 kasarigan

-0.76

Same

-0.61

same

-0.58

InvalidProtocol

-0.54

 Same

-0.54

同一个

-0.53

 mismo

-0.53

 derselben

-0.51

 demselben

-0.51

 andererseits

-0.51

POSITIVE LOGITS

sim

1.24

 simil

1.04

 similar

0.96

 SIMILAR

0.89

 المعيارى

0.88

 virtually

0.86

SIM

0.85

sim

0.83

simi

0.83

MigrationBuilder

0.82

Activations Density 0.279%

terms related to comparison and similarity

No Comments

No Known Activations