INDEX

Explanations

ellipses or continuation indicators

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 ‘‘

-0.69

ViewImports

-0.69

IBAction

-0.68

CppCodeGen

-0.61

forKey

-0.61

 Inflate

-0.60

=[]

-0.59

{{$

-0.59

LikeLiked

-0.58

Personendaten

-0.58

POSITIVE LOGITS

...

3.74

...

3.43

,...

3.00

......

2.93

)...

2.91

..."

2.81

....

2.81

-...

2.78

'...

2.76

(...

2.76

Activations Density 0.265%

ellipses or continuation indicators

No Comments

No Known Activations