INDEX

Explanations

mentions of specific geographical locations, particularly states in Australia

oai_token-act-pair · gpt-3.5-turbo

instances of specific geographical or organizational names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

DoS

-0.77

IPM

-0.65

realDonaldTrump

-0.63

 equival

-0.63

Bir

-0.62

xus

-0.61

inventoryQuantity

-0.61

GREEN

-0.61

_-

-0.61

scl

-0.61

POSITIVE LOGITS

angled

0.88

izons

0.73

 Wales

0.71

leans

0.69

 Cinema

0.69

eers

0.67

phrine

0.67

enium

0.65

utions

0.63

aldo

0.63

Activations Density 0.097%

mentions of specific geographical locations, particularly states in Australia

instances of specific geographical or organizational names

No Comments

No Known Activations