INDEX

Explanations

references to flags and their statuses in programming or configuration contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

."</

-0.79

ymce

-0.77

\"");

-0.74

😚

-0.69

"}")

-0.69

Daryl

-0.69

دور

-0.67

 Erfurt

-0.67

 selves

-0.66

onNext

-0.65

POSITIVE LOGITS

 flags

2.35

 Flag

2.29

 Flags

2.22

 flag

2.22

 FLAG

2.20

flag

2.10

flags

2.04

Flag

2.02

Flags

1.99

FLAG

1.95

Activations Density 0.047%

references to flags and their statuses in programming or configuration contexts

No Comments

No Known Activations