INDEX

Explanations

programming constructs related to variable assignments and data structures

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

 class

-0.60

RectangleBorder

-0.57

enumii

-0.57

tojas

-0.56

jenost

-0.54

]--;

-0.54

nappropriate

-0.54

servo

-0.54

 Class

-0.53

 namanya

-0.53

POSITIVE LOGITS

thenReturn

0.73

arraycopy

0.69

initWithFrame

0.58

principalTable

0.56

writerow

0.55

 localObject

0.54

 ModelExpression

0.54

DataBinding

0.53

UObject

0.50

GOTREF

0.50

Activations Density 0.319%

programming constructs related to variable assignments and data structures

No Comments

No Known Activations