INDEX

Explanations

occurrences of the word "call" in various contexts

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

ichtig

-0.63

 للمعارف

-0.62

 يتيمه

-0.61

crollView

-0.57

antaranya

-0.56

EndInit

-0.56

🏽

-0.56

wards

-0.55

 hatches

-0.55

WARDS

-0.55

POSITIVE LOGITS

 CALL

1.19

 call

1.16

 Call

1.13

 calls

1.13

 Calls

1.12

Calls

1.09

CALL

1.08

Call

1.04

calls

1.03

 calling

0.96

Activations Density 0.085%

occurrences of the word "call" in various contexts

No Comments

No Known Activations