INDEX

Explanations

phrases referencing location or context in various situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 CreateTagHelper

-0.51

ificación

-0.50

 which

-0.50

cjon

-0.49

 disponibilités

-0.48

 durata

-0.48

demment

-0.47

 artificiales

-0.46

 hinweg

-0.46

 pessoais

-0.45

POSITIVE LOGITS

 forefront

0.86

 fray

0.83

 spotlight

0.79

 limelight

0.78

 fold

0.76

 thick

0.69

findpost

0.67

mix

0.66

 HttpNotFound

0.66

saraba

0.65

Activations Density 0.338%

phrases referencing location or context in various situations

No Comments

No Known Activations