INDEX

Explanations

references to bonds and bonding 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

LoggerFactory

-0.81

 diarr

-0.77

 Arki

-0.75

 Dorothea

-0.74

XG

-0.74

 Wör

-0.73

 Whipple

-0.72

 greateſt

-0.71

Gä

-0.70

dics

-0.70

POSITIVE LOGITS

 bond

2.76

 bonds

2.65

 Bond

2.61

 Bonds

2.53

bond

2.53

 BOND

2.41

Bond

2.41

bonds

2.33

Bonds

2.20

BOND

2.04

Activations Density 0.068%

references to bonds and bonding in various contexts

No Comments

No Known Activations