INDEX

Explanations

phrases related to expressions of interest or willingness to participate in an activity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

findpost

-0.62

 fallu

-0.51

ĵo

-0.50

Erreferentziak

-0.48

umque

-0.47

----+

-0.46

 spéciales

-0.46

kuuta

-0.45

"}")

-0.45

 lenker

-0.45

POSITIVE LOGITS

 interested

2.07

 Interested

1.88

 interest

1.81

interested

1.78

Interested

1.70

 INTEREST

1.62

 Interest

1.60

INTEREST

1.57

Interest

1.54

interest

1.53

Activations Density 0.210%

phrases related to expressions of interest or willingness to participate in an activity

No Comments

No Known Activations