INDEX

Explanations

phrases that indicate definitions or explanations of terms

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

Décès

-0.80

 يتيمه

-0.78

طني

-0.69

ThroughAttribute

-0.68

 Davison

-0.68

ChildScrollView

-0.67

 mergeFrom

-0.65

 Davidson

-0.64

 Paterson

-0.63

 Bots

-0.63

POSITIVE LOGITS

 Means

2.01

Means

1.99

 mean

1.79

 MEAN

1.77

 Mean

1.77

MEAN

1.76

 means

1.73

 MEANS

1.72

mean

1.68

means

1.66

Activations Density 0.104%

phrases that indicate definitions or explanations of terms

No Comments

No Known Activations