INDEX

Explanations

mentions of the word "steam."

oai_token-act-pair · gpt-3.5-turbo

references to steam and its various applications or contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

xus

-0.77

ournal

-0.68

uala

-0.65

ROR

-0.63

iotic

-0.62

Suc

-0.60

CVE

-0.60

lr

-0.59

 Obama

-0.58

IAS

-0.58

POSITIVE LOGITS

boat

1.18

roller

1.02

boats

1.01

 locom

0.98

rolled

0.91

pipe

0.88

rollers

0.88

rolling

0.85

cream

0.83

 turbine

0.81

Activations Density 0.012%

mentions of the word "steam."

references to steam and its various applications or contexts

No Comments

No Known Activations