INDEX

Explanations

phrases indicating uncertainty or the need for clarity in communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 Roskov

-0.94

 Paglinawan

-0.79

InjectAttribute

-0.73

 beginnetje

-0.71

principalColumn

-0.70

 Wikimedijinoj

-0.70

 يتيمه

-0.69

 Ogni

-0.69

oprot

-0.66

verwijspagina

-0.64

POSITIVE LOGITS

all

1.60

 none

1.57

这一切

1.40

 None

1.33

None

1.26

all

1.24

none

1.23

 tudo

1.11

 allemaal

1.02

 tutto

1.02

Activations Density 0.242%

phrases indicating uncertainty or the need for clarity in communication

No Comments

No Known Activations