INDEX

Explanations

words or phrases that highlight quality or satisfaction in experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 ModelExpression

-0.60

Litteratur

-0.54

 hoeft

-0.53

ByExample

-0.51

ichord

-0.51

Atsauces

-0.48

 pungkas

-0.47

ГЛА

-0.47

éez

-0.47

Literatuur

-0.46

POSITIVE LOGITS

 staff

1.05

 place

0.88

 decor

0.83

 owner

0.79

 atmosphere

0.77

 prices

0.76

 environment

0.76

 wait

0.75

 manager

0.75

 service

0.74

Activations Density 0.116%

words or phrases that highlight quality or satisfaction in experiences

No Comments

No Known Activations