INDEX

Explanations

references to pairs of objects or components 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 @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

-0.83

SourceChecksum

-0.74

tagext

-0.71

 Chwiliwch

-0.71

CreateModel

-0.66

PerformLayout

-0.65

 useRef

-0.65

 Réponses

-0.64

PYX

-0.63

Хьажоргаш

-0.62

POSITIVE LOGITS

these

0.56

 themselves

0.56

 these

0.56

 виправивши

0.51

These

0.51

 These

0.51

 trous

0.48

ђу

0.47

 THESE

0.46

lerine

0.46

Activations Density 0.410%

references to pairs of objects or components in various contexts

No Comments

No Known Activations