INDEX

Explanations

occurrences of input and output stream functions and manipulations

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

Effects

-0.63

 INTERESAR

-0.60

Wam

-0.60

))[

-0.59

 Hintergrund

-0.58

爪

-0.58

Alo

-0.57

expandindo

-0.57

 hammer

-0.56

 Trix

-0.56

POSITIVE LOGITS

cout

2.01

 cout

1.79

Cout

1.61

 Cout

1.52

 Coutinho

1.15

 Couture

1.13

iostream

1.06

couts

0.96

 couture

0.89

 يتيمه

0.82

Activations Density 0.035%

occurrences of input and output stream functions and manipulations

No Comments

No Known Activations