INDEX

Explanations

records of performance metrics and achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.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

]")]

-0.49

 benessere

-0.46

扬

-0.44

 tròn

-0.44

să

-0.43

max

-0.42

 rispondere

-0.42

 rendere

-0.42

mà

-0.42

 péri

-0.41

POSITIVE LOGITS

Vidite

0.68

ValueStyle

0.64

StructEnd

0.62

 utafiti

0.61

دانشنامهٔ

0.59

%";

0.58

lotl

0.58

地说道

0.57

ipedi

0.57

IntoConstraints

0.57

Activations Density 0.180%

records of performance metrics and achievements

No Comments

No Known Activations