INDEX

Explanations

phrases related to requests and permissions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 ✭✭

-0.71

abestanden

-0.58

 Мексичка

-0.53

inola

-0.51

ällor

-0.50

BASEPATH

-0.50

nodoc

-0.49

AddTagHelper

-0.47

litude

-0.46

hombo

-0.46

POSITIVE LOGITS

 request

3.41

 requests

3.12

request

3.02

 requesting

2.87

 Request

2.85

 REQUEST

2.69

 requested

2.69

Request

2.68

 Requests

2.67

requests

2.52

Activations Density 0.834%

phrases related to requests and permissions

No Comments

No Known Activations