INDEX

Explanations

references to the word "tip" and related expressions

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

CodeAttribute

-0.59

istoitu

-0.59

LError

-0.56

AccessException

-0.56

TableAdapter

-0.55

BeginContext

-0.55

 propOrder

-0.54

AsUp

-0.51

 обращения

-0.49

EndContext

-0.49

POSITIVE LOGITS

tip

1.28

 tips

1.15

✨:

0.99

SEVERE

0.97

Tip

0.96

Tip

0.91

tip

0.87

 TIPS

0.84

 severe

0.83

 severity

0.83

Activations Density 0.089%

references to the word "tip" and related expressions

No Comments

No Known Activations