INDEX

Explanations

phrases that denote limits or boundaries of studies and guidelines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

PhysRevLett

-0.58

 đốc

-0.57

الدراسه

-0.57

 estimés

-0.51

amssymb

-0.50

 препратки

-0.50



-0.49

AccessException

-0.49

uxxxx

-0.49

zzar

-0.48

POSITIVE LOGITS

 purpose

1.07

本文

1.03

aim

0.95

今回は

0.91

purpose

0.89

 objective

0.87

Aim

0.87

 aims

0.84

本章

0.84

 Purpose

0.84

Activations Density 0.639%

phrases that denote limits or boundaries of studies and guidelines

No Comments

No Known Activations