INDEX

Explanations

phrases that refer to the consequences or effects of actions or situations

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

excellents

-0.71

ogeneous

-0.70

buttonBar

-0.69

esine

-0.67

skr

-0.66

Gus

-0.66

jsonwebtoken

-0.66

 CreateTagHelper

-0.65

 menga

-0.64

rophore

-0.63

POSITIVE LOGITS

 impact

2.46

 Impact

2.33

 impacts

2.32

 IMPACT

2.32

impact

2.22

 Impacts

2.21

Impact

2.15

Impacts

2.14

IMPACT

2.12

 impacting

2.02

Activations Density 0.062%

phrases that refer to the consequences or effects of actions or situations

No Comments

No Known Activations