INDEX

Explanations

references to negotiations or related discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Jefus

-1.23

 myſelf

-1.21

 whoſe

-1.18

 raiſ

-1.15

Efq

-1.12

 Monfieur

-1.12

 againſt

-1.08

 deſt

-1.06

 himſelf

-1.06

 becauſe

-1.05

POSITIVE LOGITS

<h2>

0.71

0.60

<h6>

0.59

<eos>

0.56

 negotiations

0.56

0.55

↵↵

0.54

0.50

Activations Density 0.213%

references to negotiations or related discussions

No Comments

No Known Activations