INDEX

Explanations

connections and relationships between distinct items or concepts

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 estimated

-0.50

MENAFN

-0.48

={()

-0.46

 ThemeData

-0.46

de

-0.46

Mol

-0.46

jsonwebtoken

-0.45

undes

-0.45

éal

-0.45

consts

-0.45

POSITIVE LOGITS

 differing

0.76

 birbir

0.76

それぞれ

0.73

 saling

0.71

 respectively

0.70

 eachother

0.69

之间

0.69

 unison

0.67

 respective

0.67

 Diſ

0.67

Activations Density 0.775%

connections and relationships between distinct items or concepts

No Comments

No Known Activations