INDEX

Explanations

specific mentions of the word "Journal."

oai_token-act-pair · gpt-3.5-turbo

references to journals or publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

holders

-0.73

minus

-0.69

 theirs

-0.68

creen

-0.66

 brightly

-0.61

 Pric

-0.61

rises

-0.61

rolet

-0.60

grades

-0.60

stairs

-0.60

POSITIVE LOGITS

osphere

1.04

istic

1.03

ists

1.01

ist

0.99

 Sentinel

0.98

ism

0.97

istically

0.94

ournals

0.92

 Editors

0.86

ocular

0.84

Activations Density 0.040%

specific mentions of the word "Journal."

references to journals or publications

No Comments

No Known Activations