INDEX

Explanations

references to groups of people and their interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

be

-1.19

NotBe

-0.71

queryInterface

-0.67

awaiter

-0.66

 бути

-0.66

 být

-0.65

 olla

-0.64

 باشد

-0.64

localctx

-0.62

 być

-0.60

POSITIVE LOGITS

 propOrder

0.77

can

0.70

are

0.65

 must

0.61

 cannot

0.59

 might

0.56

vertebrates

0.55

varlak

0.54

 would

0.54

 sagde

0.53

Activations Density 0.430%

references to groups of people and their interactions

No Comments

No Known Activations