INDEX

Explanations

expressions of strength or intensity

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

Not in Any Lists

No Comments

Negative Logits

enumi

-0.75

GetMapping

-0.69

Datuak

-0.68

verifyException

-0.66

følgelig

-0.63

 برانيه

-0.61

 reindeer

-0.59

 AudioClip

-0.59

 interchangeably

-0.59

edos

-0.58

POSITIVE LOGITS

 strong

3.63

 Strong

3.47

strong

3.47

Strong

3.40

 STRONG

3.17

STRONG

2.99

 stronger

2.65

 strongest

2.59

 Stronger

2.31

 sterke

2.31

Activations Density 0.091%

expressions of strength or intensity

No Comments

No Known Activations