INDEX

Explanations

connector words and pronouns that indicate relationships or references within sentences

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

GIVEREF

-0.83

URLException

-0.68

 виправивши

-0.66

eleste

-0.66

 AssemblyVersion

-0.65

 typelib

-0.65

UrlResolution

-0.64

ngrx

-0.61

oredCriteria

-0.61

حوالہ

-0.60

POSITIVE LOGITS

basicConfig

0.73

<bos>

0.53

ี

0.48

 THEOREM

0.47

 Visite

0.46

vara

0.45

 Katharine

0.45

だけは

0.43

лья

0.43

 Shakspeare

0.43

Activations Density 0.621%

connector words and pronouns that indicate relationships or references within sentences

No Comments

No Known Activations