INDEX

Explanations

instances of the word "enable" or its variations 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

 كومونز

-0.84

 useRef

-0.81

SplashScreen

-0.76

TRS

-0.75

 extérieures

-0.74

 CreateTagHelper

-0.73

bcrypt

-0.71

osc

-0.70

 Wikispecies

-0.69

chloro

-0.69

POSITIVE LOGITS

 enable

2.00

 Enable

1.87

 enabling

1.86

 enables

1.85

 enabled

1.76

 Enables

1.74

 ENABLE

1.66

Enable

1.62

Enabling

1.59

enable

1.58

Activations Density 0.071%

instances of the word "enable" or its variations in various contexts

No Comments

No Known Activations