INDEX

Explanations

the word "aur" repeated in texts

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or geographical terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

SO

-0.69

 streaming

-0.64

 stream

-0.63

 Bottom

-0.61

Lo

-0.61

 streamed

-0.61

tie

-0.60

 hearts

-0.60

 secession

-0.60

 streams

-0.60

POSITIVE LOGITS

aur

4.64

auri

2.65

aurus

1.89

aura

1.70

au

1.14

urion

1.14

 Saur

1.07

Aur

1.05

urus

1.00

aul

0.97

Activations Density 0.011%

the word "aur" repeated in texts

references to specific locations or geographical terms

No Comments

No Known Activations