INDEX

Explanations

phrases specifically related to conditions and their descriptions 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 @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 astray

-0.84

BYTES

-0.81

>−

-0.80

 flèche

-0.76

 AppColors

-0.73

揄

-0.71

 respiro

-0.71

üyük

-0.71

Bam

-0.70

 significativos

-0.69

POSITIVE LOGITS

 conditions

1.97

 Conditions

1.73

 condition

1.72

conditions

1.70

Condition

1.67

Conditions

1.65

 CONDITIONS

1.60

 Condition

1.57

 CONDITION

1.49

condition

1.48

Activations Density 0.060%

phrases specifically related to conditions and their descriptions in various contexts

No Comments

No Known Activations