INDEX

Explanations

code and function definitions, specifically focusing on variable statuses and object properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

]<<"

-0.60

SequentialGroup

-0.59

&&

-0.51

IUrlHelper

-0.48

&&

-0.47

rund

-0.47

AddWithValue

-0.47

findpost

-0.45

 Herring

-0.44

 Chasse

-0.44

POSITIVE LOGITS

==

0.97

===

0.87

==

0.76

!=

0.73

==$

0.69

()==

0.69

!==

0.66

>=

0.66

']==

0.65

==-

0.64

Activations Density 0.175%

code and function definitions, specifically focusing on variable statuses and object properties

No Comments

No Known Activations