INDEX

Explanations

references to alcohol consumption or related themes of drunkenness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

Revenir

-0.62

 referrerpolicy

-0.62

ंदीखरीदारी

-0.60

 وتسجيلات

-0.57

Démographie

-0.56

Становништво

-0.55

Atsauces

-0.54

 跳转至

-0.54

racha

-0.54

 ProtoMessage

-0.54

POSITIVE LOGITS

Opus

0.55

 يتيمه

0.50

PreferredItem

0.50

 activism

0.49

 Operator

0.48

 greateſt

0.47

ніципа

0.47

 totul

0.47

:✨

0.47

Lyd

0.47

Activations Density 0.123%

references to alcohol consumption or related themes of drunkenness

No Comments

No Known Activations