INDEX

Explanations

mention of the word "need" and its variations in different contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

:✨

-0.74

ffions

-0.68

httphttps

-0.68

 BoxDecoration

-0.67

colhead

-0.66

 manslaughter

-0.65

Remarks

-0.64

 portátiles

-0.63

iniums

-0.61

Personendaten

-0.61

POSITIVE LOGITS

 need

3.59

 Need

3.13

need

3.12

Need

2.99

 NEED

2.85

NEED

2.75

 needs

2.68

 Needs

2.40

needs

2.31

 besoin

2.25

Activations Density 0.133%

mention of the word "need" and its variations in different contexts

No Known Activations