INDEX

Explanations

numerical data associated with experimental results

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

GEBURTSDATUM

-0.90

Vidite

-0.87

NameInMap

-0.77

 '\\;'

-0.74

 AssemblyVersion

-0.61

RTLD

-0.60

Geplaatst

-0.58

 "..\..\

-0.57

writeFieldEnd

-0.55

 "..\..\..\

-0.55

POSITIVE LOGITS

 ExecuteAsync

0.76

’

0.69

multirow

0.64

közi

0.61

0.60

kranz

0.57

 luego

0.57

 kaynağından

0.57

}{*}{}

0.55

ocell

0.54

Activations Density 0.392%

numerical data associated with experimental results

No Comments

No Known Activations