INDEX

Explanations

terms related to usernames and authentication in code and configuration contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

WriteBarrier

-1.20

TCL

-0.90

]")]

-0.90

ollectionView

-0.89

 useRef

-0.89

 الرياضيه

-0.89

NameInMap

-0.88

toc

-0.88

}-*/;

-0.88

`"

-0.87

POSITIVE LOGITS

setUsername

0.69

 Oakes

0.64

Hampton

0.62

ous

0.60

beqa

0.59

empatan

0.58

一个

0.58

 שוליים

0.58

Frat

0.57

 referrerpolicy

0.57

Activations Density 0.113%

terms related to usernames and authentication in code and configuration contexts

No Comments

No Known Activations