INDEX

Explanations

numerical values related to scores or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ագրություններ

-0.64

You

-0.64

-0.61

Viitteet

-0.61

 They

-0.60

It

-0.60

The

-0.60

‘

-0.57

If

-0.54

And

-0.53

POSITIVE LOGITS

SourceChecksum

1.04

TagMode

0.93

 تكبرها

0.87

 contextLoads

0.82

Portail

0.77

 Signalez

0.76

 cherchés

0.72

 tartalomajánló

0.69

↵↵↵↵↵↵↵↵↵↵↵↵↵

0.67

↵↵↵↵↵↵↵↵↵↵↵↵↵↵

0.66

Activations Density 0.374%

numerical values related to scores or measurements

No Comments

No Known Activations