INDEX

Explanations

punctuation marks and formatting elements in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Autoritní

-0.75

aarrggbb

-0.62

 الرياضيه

-0.61

fjspx

-0.61

 autorytatywna

-0.61

 للاسماء

-0.60

statt

-0.59

"+"

-0.56

 "/")

-0.56

 OFDb

-0.55

POSITIVE LOGITS

 interviewer

0.81

 Transcript

0.73

Interviewer

0.72

 transcript

0.66

 announcer

0.64

 Yeah

0.60

Yeah

0.59

Transcript

0.59

Audience

0.59

Activations Density 0.345%

punctuation marks and formatting elements in the text

No Comments

No Known Activations