INDEX

Explanations

mentions of trips and traveling

oai_token-act-pair · gpt-3.5-turbo

references to trips or travel experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Pie

-0.62

=#

-0.62

tymology

-0.61

Sta

-0.59

 taxp

-0.58

 relational

-0.56

 Reign

-0.55

 substantive

-0.55

ĪĴ

-0.55

ledged

-0.53

POSITIVE LOGITS

 abroad

1.13

 itiner

0.99

ods

0.98

ogue

0.87

wire

0.80

 planner

0.79

 overseas

0.79

è¦ļéĨĴ

0.79

itiz

0.79

 booked

0.77

Activations Density 0.046%

mentions of trips and traveling

references to trips or travel experiences

No Comments

No Known Activations