INDEX

Explanations

dialogue or conversational exchanges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Notably

-0.80

 cref

-0.76

 relevantes

-0.75

 impactful

-0.74

 souhaitez

-0.72

 Importantly

-0.72

 curated

-0.72

TLDR

-0.71

 Ensuring

-0.71

 relevancia

-0.70

POSITIVE LOGITS

 daß

1.05

 muß

1.01

 müßte

0.96

 Daß

0.94

 mußte

0.92

 mußten

0.91

 Schluß

0.89

 biß

0.86

 damned

0.83

 läßt

0.80

Activations Density 0.508%

dialogue or conversational exchanges

No Comments

No Known Activations