INDEX

Explanations

the term "subject" in various contexts related to classification or categorization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

✨:

-0.83

 craw

-0.80

ForRow

-0.79

 dandy

-0.76

раздо

-0.76

Efq

-0.74

="/">

-0.74

 membuk

-0.71

SPS

-0.71

 flocc

-0.71

POSITIVE LOGITS

 subject

1.93

 Subject

1.79

subject

1.78

 subjects

1.73

 SUBJECT

1.70

Subject

1.68

SUBJECT

1.65

 Subjects

1.61

subjects

1.54

setSubject

1.53

Activations Density 0.062%

the term "subject" in various contexts related to classification or categorization

No Comments

No Known Activations