INDEX

Explanations

the presence of various forms of the suffix 'te', indicating words related to actions or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/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.21.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

apunov

-0.56

namespace

-0.54

💼

-0.54

Démographie

-0.54

évaluateur

-0.54

KommentareTeilen

-0.49

MigrationBuilder

-0.49

ness

-0.48

 سكانية

-0.48

Parcelize

-0.46

POSITIVE LOGITS

fisk

0.53

meyer

0.53

tuer

0.52

meier

0.51

 invokingState

0.50

 IndexPath

0.50

amet

0.49

treat

0.49

Jereo

0.48

lagen

0.48

Activations Density 0.128%

the presence of various forms of the suffix 'te', indicating words related to actions or processes

No Comments

No Known Activations