INDEX

Explanations

patterns or structures related to numerical data or indices

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

UnusedPrivate

-0.67

-0.55

<u>

-0.52

 indeed

-0.52

DialogContent

-0.52

drav

-0.51

 Multin

-0.51

 simply

-0.51

 SIMBAD

-0.50

/******/

-0.50

POSITIVE LOGITS

ConstraintMaker

0.72

djangoproject

0.68

 تانيه

0.66

.}}

0.66

ContentLoaded

0.64

bufio

0.64

ThroughAttribute

0.60

 Мексичка

0.59

']))

0.58

abetes

0.56

Activations Density 0.949%

patterns or structures related to numerical data or indices

No Comments

No Known Activations