INDEX

Explanations

references to psychological or emotional states and their implications

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

ScopeManager

-0.78

AddHtmlAttribute

-0.68

 ―――――

-0.59

twimg

-0.59

NUMX

-0.58

argout

-0.57

 Վերցված

-0.57

 JpaRepository

-0.56

ſelves

-0.55

 ་་

-0.55

POSITIVE LOGITS

 whereas

1.10

whereas

0.98

 Whereas

0.95

Whereas

0.92

 unlike

0.76

unlike

0.68

不像

0.63

 sedangkan

0.59

 compared

0.57

 متعلقه

0.54

Activations Density 0.612%

references to psychological or emotional states and their implications

No Comments

No Known Activations