INDEX

Explanations

temporal indicators or transitions in narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

InputBorder

-0.87

 AssemblyTitle

-0.79

stdc

-0.78

 TextInputType

-0.75

offsetof

-0.70

nestjs

-0.70

 FontWeight

-0.69

 &___

-0.66

 McDonough

-0.66

mapStateToProps

-0.65

POSITIVE LOGITS

 later

1.62

later

1.54

Later

1.49

 Later

1.46

 LATER

1.39

 afterwards

1.23

 späteren

1.18

 afterward

1.17

 subsequent

1.12

sequent

1.10

Activations Density 0.116%

temporal indicators or transitions in narrative

No Comments

No Known Activations