INDEX

Explanations

names of individuals, likely from a specific cultural context

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

-0.60

’

-0.50

-0.48

“

-0.47

 singola

-0.46

at

-0.45

od

-0.43

↵↵

-0.42

POSITIVE LOGITS

tvguidetime

0.98

rawDesc

0.96

 initComponents

0.96

 Roskov

0.93

 ModelExpression

0.93

RenderAtEndOf

0.92

parsedMessage

0.90

SourceChecksum

0.87

 ―――――

0.85

 ProtoMessage

0.84

Activations Density 0.340%

names of individuals, likely from a specific cultural context

No Comments

No Known Activations