INDEX

Explanations

numerical values associated with statistical results

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 snippetHide

-1.03

mybatisplus

-0.99

Hauptartikel

-0.99

 getItemId

-0.97

styleType

-0.91

 Shakspeare

-0.91

 itſelf

-0.91

 wireType

-0.90

 дописавши

-0.90

 initComponents

-0.89

POSITIVE LOGITS

/\.

0.62

0.61

(.

0.58

 Bote

0.57

cancellation

0.57

=.

0.56

 semi

0.55

Че

0.55

ENIA

0.54

.$.

0.52

Activations Density 0.252%

numerical values associated with statistical results

No Comments

No Known Activations