INDEX

Explanations

references to "higher" or "higher education."

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

üttel

-0.57

Mil

-0.56

حوالہ

-0.56

さ

-0.52

ез

-0.49

Kil

-0.48

AnchorStyles

-0.48

Ala

-0.48

koff

-0.48

buf

-0.47

POSITIVE LOGITS

 higher

3.04

Higher

2.91

 Higher

2.88

higher

2.87

 HIGHER

2.72

 höher

1.92

 höhere

1.88

 höheren

1.82

 högre

1.70

 hoger

1.61

Activations Density 0.126%

references to "higher" or "higher education."

No Comments

No Known Activations