INDEX

Explanations

instances of the word "call" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Paisley

-0.76

wendi

-0.74

Endian

-0.72

acen

-0.67

djangoproject

-0.67

 ergo

-0.66

stuffs

-0.66

 endured

-0.66

mentes

-0.65

 Elsie

-0.64

POSITIVE LOGITS

 call

1.92

 CALL

1.85

 calls

1.77

 Call

1.75

 Calls

1.71

call

1.66

CALL

1.65

Call

1.65

Calls

1.61

calls

1.58

Activations Density 0.117%

instances of the word "call" and its variations

No Comments

No Known Activations