INDEX

Explanations

instances of the word "call" and its variations in various contexts, suggesting a focus on communication or requests

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

 يتيمه

-0.76

 postIndex

-0.70

iastical

-0.64

enment

-0.63

ndrome

-0.63

 للمعارف

-0.60

 AssemblyCulture

-0.60

 Савезне

-0.58

ichtig

-0.57

EndInit

-0.57

POSITIVE LOGITS

 CALL

1.35

 Call

1.31

 Calls

1.30

 call

1.28

 calls

1.27

CALL

1.23

Call

1.22

Calls

1.21

calls

1.15

call

1.09

Activations Density 0.108%

instances of the word "call" and its variations in various contexts, suggesting a focus on communication or requests

No Comments

No Known Activations