INDEX

Explanations

assertions of correctness or rightness in a discussion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RectangleBorder

-0.99

tagHelperRunner

-0.73

TypedDataSet

-0.72

DockStyle

-0.69

MENAFN

-0.68

AutoresizingMask

-0.66

LEncoder

-0.65

VideoCapture

-0.65

oredCriteria

-0.64

expandindo

-0.63

POSITIVE LOGITS

 correct

0.59

 errado

0.57

twimg

0.57

 truth

0.54

 désolés

0.53

]-->

0.53

 verdad

0.52

 correcto

0.51

 totales

0.50

 correctness

0.50

Activations Density 0.132%

assertions of correctness or rightness in a discussion

No Comments

No Known Activations