INDEX

Explanations

phrases expressing uncertainty or hesitation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/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.20.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

culin

-0.49

<bos>

-0.44

 missing

-0.42

よりは

-0.42

 deve

-0.40

atchewan

-0.40

begin

-0.39

NotSupported

-0.39

dont

-0.39

avoir

-0.38

POSITIVE LOGITS

no

1.02

 nothing

1.01

 doInBackground

0.92

 nada

0.92

 nenhum

0.90

CppMethod

0.88

 CreateTagHelper

0.88

 ningún

0.85

nothing

0.82

 ninguno

0.82

Activations Density 0.327%

phrases expressing uncertainty or hesitation

No Comments

No Known Activations