INDEX

Explanations

specific event markers or actions in a narrative context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 termica

-0.54

 jspb

-0.54

 Acad

-0.46

republik

-0.44

spooky

-0.43

 knots

-0.43

Acad

-0.43

سطس

-0.42

 espin

-0.41

ắn

-0.41

POSITIVE LOGITS

rungsseite

0.81

Билгалдахарш

0.63

tagext

0.62

contentLoaded

0.61

 absentee

0.59

:+:

0.59

WithIOException

0.57

 оригіналу

0.54

CreateModel

0.53

 meanwhile

0.53

Activations Density 0.187%

specific event markers or actions in a narrative context

No Comments

No Known Activations