INDEX

Explanations

references to statistical data and numerical attributes related to sports or performance metrics

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

 كومونز

-0.94

 becauſe

-0.91

 itſelf

-0.89

 Houſe

-0.89

 Diſ

-0.89

 ſeveral

-0.88

 houſe

-0.87

 laſt

-0.85

 themſelves

-0.84

 deſt

-0.84

POSITIVE LOGITS

Le

0.58

</em>

0.55

 that

0.53

is

0.52

“

0.49

TextBoxColumn

0.48

</strong>

0.48

0.47

Activations Density 0.036%

references to statistical data and numerical attributes related to sports or performance metrics

No Comments

No Known Activations