INDEX

Explanations

terms related to a specific geographical location, specifically the Bay Area

oai_token-act-pair · gpt-3.5-turbo

mentions of the Bay Area

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

mble

-0.75

matter

-0.72

terday

-0.69

anson

-0.67

etsk

-0.67

iferation

-0.64

×ķ

-0.63

ACTED

-0.62

 Beir

-0.61

 heartbeat

-0.61

POSITIVE LOGITS

onet

1.29

esian

1.19

 Area

0.84

deen

0.80

town

0.79

ou

0.79

hawks

0.77

leys

0.74

front

0.73

rina

0.73

Activations Density 0.022%

terms related to a specific geographical location, specifically the Bay Area

mentions of the Bay Area

No Comments

No Known Activations