INDEX

Explanations

mentions of significant individuals and their roles or actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 незавершена

-0.82

хьтан

-0.79

 Majefty

-0.77

 esternos

-0.77

 ComVisible

-0.77

kosh

-0.76

zeptember

-0.75

 Chriftian

-0.72

 doubtnut

-0.71

 becauſe

-0.71

POSITIVE LOGITS

PerformLayout

0.48

 attended

0.48

 Whilst

0.48

”.

0.47

ando

0.47

id

0.44

 organised

0.44

???

0.44

Whilst

0.43

”,

0.43

Activations Density 0.069%

mentions of significant individuals and their roles or actions

No Comments

No Known Activations