INDEX

Explanations

terms related to geographical districts and educational institutions within them

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 unve

-0.72

 shenan

-0.71

 unlaw

-0.70

 eyel

-0.68

 fortn

-0.67

 impractica

-0.64

 accla

-0.63

 unce

-0.62

 ROBER

-0.61

 intersper

-0.60

POSITIVE LOGITS

 district

1.46

District

1.46

 District

1.42

district

1.40

 districts

1.29

 DISTRICT

1.24

DISTRICT

1.14

 Districts

1.10

districts

1.04

 distrito

0.87

Activations Density 0.082%

terms related to geographical districts and educational institutions within them

No Comments

No Known Activations