INDEX

Explanations

terms related to alignment and positioning in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

principalColumn

-1.16

Jeografia

-1.04

الحياه

-0.96

expandindo

-0.91

 HttpNotFound

-0.89

ⓧ

-0.89

zzleHttp

-0.89

 يتيمه

-0.88

ंदीखरीदारी

-0.87

Hochspringen

-0.87

POSITIVE LOGITS

 align

0.83

 aligned

0.83

 alignment

0.83

 aligns

0.78

 aligning

0.76

 Alignment

0.73

 Align

0.68

 ALIGN

0.63

alignment

0.61

 alin

0.60

Activations Density 0.240%

terms related to alignment and positioning in various contexts

No Comments

No Known Activations