INDEX

Explanations

conditional statements or phrases indicating hypothetical scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_mlp_out

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

 bezeichneter

-0.81

")));

-0.79

dafx

-0.78

énario

-0.77

'},

-0.75

期刊论文

-0.74

"):

-0.74

featureID

-0.73

-0.72

exitRule

-0.71

POSITIVE LOGITS

you

0.60

Péri

0.50

we

0.48

vato

0.47

YOU

0.47

he

0.46

 however

0.46

 bulunabilir

0.44

 human

0.42

льзя

0.42

Activations Density 0.294%

conditional statements or phrases indicating hypothetical scenarios

No Comments

No Known Activations