INDEX

Explanations

words related to cryptocurrency

oai_token-act-pair · gpt-3.5-turbo

mentions of cryptocurrency and related terminology

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Loving

-0.76

NING

-0.72

 Phelps

-0.68

 Yemeni

-0.66

 Hanson

-0.63

witz

-0.63

Ng

-0.63

ALS

-0.62

ABE

-0.61

UGH

-0.61

POSITIVE LOGITS

ozo

1.33

ographically

1.30

ographers

1.11

onyms

1.08

analysis

1.07

ographer

1.03

ogram

1.03

ographic

1.03

ograms

1.02

opsy

1.02

Activations Density 0.014%

words related to cryptocurrency

mentions of cryptocurrency and related terminology

No Comments

No Known Activations