INDEX

Explanations

occurrences of the word "notice"

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

expandindo

-0.67

 ISNI

-0.66

Pranala

-0.65

Биография

-0.65

readFileSync

-0.63

hdashline

-0.61

OrWhiteSpace

-0.60

ISupport

-0.59

Населення

-0.57

writeField

-0.57

POSITIVE LOGITS

 notice

3.02

 Notice

2.84

Notice

2.74

notice

2.73

 NOTICE

2.52

 notices

2.49

NOTICE

2.35

 Notices

2.35

Notices

2.23

notices

2.03

Activations Density 0.084%

occurrences of the word "notice"

No Comments

No Known Activations