INDEX

Explanations

terms related to methodologies and evaluations in scientific research

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

idalgo

-0.70

ugeot

-0.67

Jop

-0.64

 ANIM

-0.64

\"%

-0.64

katan

-0.63

 Rptr

-0.62

Cô

-0.60

ræ

-0.60

ThemeOverlay

-0.59

POSITIVE LOGITS

↵↵

1.58

↵↵↵

1.11

↵↵↵↵

1.10

↵

1.06

↵↵↵↵↵

1.05

↵↵↵↵↵↵

0.98

[toxicity=0]

0.93

↵↵↵↵↵↵↵↵

0.87

<eos>

0.87

<h2>

0.86

Activations Density 0.288%

terms related to methodologies and evaluations in scientific research

No Comments

No Known Activations