INDEX

Explanations

interactions and relationships between characters

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<table>

-0.49

 samfun

-0.46

 shape

-0.41

팩

-0.41

 grunn

-0.41

ukul

-0.41

-0.40

 attesa

-0.39

domain

-0.39

 access

-0.39

POSITIVE LOGITS

principalColumn

1.31

 whom

1.01

MemoryWarning

1.00

GraphicsUnit

0.98

MockBean

0.95

 CreateTagHelper

0.94

StoryboardSegue

0.92

whom

0.91

WithIOException

0.88

 FetchType

0.86

Activations Density 0.371%

interactions and relationships between characters

No Comments

No Known Activations