INDEX

Explanations

numerical comparisons and modifications 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

adhé

-0.58

teborg

-0.46

 CreateTagHelper

-0.46

presenta

-0.45

 пред

-0.44

compose

-0.43

entre

-0.43

ران

-0.43

ன்று

-0.43

thâu

-0.43

POSITIVE LOGITS

Бахар

0.82

EDEFAULT

0.78

ftagPool

0.74

MemoryWarning

0.69

SuppressLint

0.64

+#+

0.63

 NSCoder

0.63

 oprot

0.62

 naman

0.61

WebVitals

0.60

Activations Density 2.170%

numerical comparisons and modifications in various contexts

No Comments

No Known Activations