INDEX

Explanations

connections between various elements and how they are intricately woven together

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 surla

-0.69

 nakalista

-0.68

 cheeks

-0.68

 Shams

-0.68

 cheek

-0.64

GEBURTSDATUM

-0.63

 Mirrors

-0.61

blit

-0.61

Blit

-0.61

 toshiba

-0.60

POSITIVE LOGITS

 thread

1.17

 threads

1.15

 wire

1.15

 rope

1.13

 cables

1.07

 cable

1.07

 ropes

1.06

 Thread

1.06

thread

1.05

 Rope

1.02

Activations Density 0.553%

connections between various elements and how they are intricately woven together

No Comments

No Known Activations