INDEX

Explanations

method definitions and overrides, specifically for `toString` and `equals`

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

Hochspringen

-0.63

 digress

-0.51

 setType

-0.48

 Ceux

-0.47

Duff

-0.47

Tikang

-0.46

 tiết

-0.46

 LUMP

-0.45

 samarbeid

-0.45

هرست

-0.45

POSITIVE LOGITS

 oprot

1.18

 hashCode

1.02

AntiForgeryToken

1.01

 mergeFrom

0.91

PrototypeOf

0.90

EDEFAULT

0.83

AutoScale

0.83

IsContent

0.76

rungsseite

0.76

 toString

0.76

Activations Density 0.065%

method definitions and overrides, specifically for `toString` and `equals`

No Comments

No Known Activations