INDEX

Explanations

references to earlier sections of the text or citations regarding information discussed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

#+#

-0.74

 sleep

-0.57

kloped

-0.55

orgs

-0.49

 useState

-0.49

Cliquez

-0.49

oci

-0.47

ientôt

-0.46

[]

-0.46

tences

-0.45

POSITIVE LOGITS

 aforementioned

1.06

 aforesaid

1.01

 above

0.98

above

0.97

 foregoing

0.89

 acima

0.86

 powy

0.83

mentioned

0.83

 oben

0.83

 mencionado

0.81

Activations Density 0.259%

references to earlier sections of the text or citations regarding information discussed

No Comments

No Known Activations