INDEX

Explanations

references to specific methodologies or processes in scientific 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

Efq

-0.79

 Majefty

-0.65

 theſe

-0.65

 Theſe

-0.64

 thoſe

-0.63

 ſeveral

-0.63

 Acht

-0.61

'));

-0.61

 myſelf

-0.61

ipedi

-0.59

POSITIVE LOGITS

SourceChecksum

0.76

 AssemblyVersion

0.71

fromCharCode

0.65

 numerus

0.64

PullParser

0.60

ImageContext

0.60

apimachinery

0.56

dafx

0.55

 insuffisamment

0.55

UnknownFieldSet

0.50

Activations Density 1.343%

references to specific methodologies or processes in scientific contexts

No Comments

No Known Activations