INDEX

Explanations

the term "ordinary" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

Corn

-0.61

ensburg

-0.61

 simila

-0.58

tieve

-0.57

 Myster

-0.57

ovács

-0.56

COR

-0.56

 Corn

-0.55

es

-0.55

 completeness

-0.55

POSITIVE LOGITS

 חיצוניים

0.89

totally

0.80

 hesitate

0.78

Autoritní

0.76

 jdbcTemplate

0.74

 MainAxisSize

0.73

WriteTagHelper

0.73

 MessageBoxIcon

0.72

TextWatcher

0.70

 يتيمه

0.69

Activations Density 0.038%

the term "ordinary" in various contexts

No Comments

No Known Activations