INDEX

Explanations

negative or critical sentiments in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 Maximize

-0.57

 fidé

-0.55

 cuantos

-0.55

äumt

-0.55

Activated

-0.54

aarrggbb

-0.54

Upgradeable

-0.54

իր

-0.53

 ersch

-0.52

 attiv

-0.52

POSITIVE LOGITS

InjectAttribute

0.81

__*/

0.75

 Signalez

0.68

 mergeFrom

0.66

AsUp

0.65

LikeLike

0.65

 jsonify

0.64

HtmlAttribute

0.59

 تضيفلها

0.59

 CallOverrides

0.59

Activations Density 0.213%

negative or critical sentiments in the text

No Comments

No Known Activations