INDEX

Explanations

references to responsibilities and duties

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

gad

-0.58

leg

-0.53

 Réponses

-0.52

cdn

-0.52

ot

-0.51

epr

-0.51

PhysRevLett

-0.50

եց

-0.50

観

-0.49

öff

-0.49

POSITIVE LOGITS

sibilities

2.08

IBILITIES

1.30

 Infórmanos

0.86

StructEnd

0.81

 समीक्षाओं

0.80

 виправивши

0.77

InitVars

0.74

*__

0.74

forName

0.73

 InputDecoration

0.73

Activations Density 0.112%

references to responsibilities and duties

No Comments

No Known Activations