INDEX

Explanations

discussions about accomplishments, challenges, and criticisms in a narrative context

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

protoc

-0.58

argli

-0.56

Jeografia

-0.51

holtz

-0.50

省市镇

-0.50

numerusform

-0.48

orszá

-0.47

rister

-0.47

rrggbb

-0.47

rache

-0.47

POSITIVE LOGITS

 toujours

0.74

 siempre

0.73

今回も

0.73

 always

0.72

Always

0.70

always

0.70

 Always

0.67

 πάντα

0.64

 Toujours

0.64

 sempre

0.64

Activations Density 0.236%

discussions about accomplishments, challenges, and criticisms in a narrative context

No Comments

No Known Activations