INDEX

Explanations

variations of the word "similar" indicating comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

حياته

-0.60

MLLoader

-0.60

yves

-0.59

ValueStyle

-0.56

ubourg

-0.56

achios

-0.55

DotNetBar

-0.55

 surla

-0.54

UrlResolution

-0.54

 normally

-0.54

POSITIVE LOGITS

 minded

0.71

lity

0.69

ily

0.65

 circonstances

0.65

 thereto

0.64

ITIES

0.63

 nhau

0.63

 görül

0.61

minded

0.61

 circonst

0.61

Activations Density 0.228%

variations of the word "similar" indicating comparisons

No Comments

No Known Activations