INDEX

Explanations

questions and statements starting with "Is" or "Does."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Theſe

-1.09

 Beſ

-0.79

 protoimpl

-0.78

 becauſe

-0.77

 ſeveral

-0.75

INSEE

-0.74

richTextPanel

-0.74

 مشين

-0.73

 ―――――

-0.72

DeepCopy

-0.72

POSITIVE LOGITS

Is

3.66

Is

3.53

Are

1.75

Does

1.66

Are

1.66

Was

1.64

 Does

1.59

getIs

1.58

IS

1.57

Was

1.56

Activations Density 0.094%

questions and statements starting with "Is" or "Does."

No Comments

No Known Activations