INDEX

Explanations

locations mentioned in news articles

oai_token-act-pair · gpt-3.5-turbo

mentions of locations or proximity to places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

BILL

-0.80

alian

-0.74

ãĥīãĥ©

-0.73

oeuv

-0.70

azeera

-0.70

Written

-0.69

oleon

-0.69

UX

-0.67

gear

-0.67

etti

-0.67

POSITIVE LOGITS

shore

0.95

 midnight

0.82

sighted

0.80

 campus

0.80

 Bethlehem

0.77

 Interstate

0.74

 Yellowstone

0.73

 Coff

0.72

 Corpus

0.72

 Yosemite

0.72

Activations Density 0.044%

locations mentioned in news articles

mentions of locations or proximity to places

No Comments

No Known Activations