INDEX

Explanations

references to specific subjects or topics in the text

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



-0.72

osu

-0.71

 lein

-0.71

 Coff

-0.71

 Agamemnon

-0.70

 Phry

-0.70

 Rosalie

-0.69

enderror

-0.68

 Dubuque

-0.68

RectangleBorder

-0.68

POSITIVE LOGITS

 THIS

1.49

 this

1.46

THIS

1.39

this

1.27

This

1.25

 This

1.24

 esta

1.04

 este

0.98

 بهذا

0.96

 questa

0.96

Activations Density 0.357%

references to specific subjects or topics in the text

No Comments

No Known Activations