INDEX

Explanations

words related to geographic locations, specifically focusing on land or countries

oai_token-act-pair · gpt-3.5-turbo

references to geographical locations or place names

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

 cumbers

-0.91

 millenn

-0.78

 tremend

-0.77

ongyang

-0.71

idium

-0.70

 undermin

-0.67

SOURCE

-0.67

displayText

-0.66

berus

-0.64

interest

-0.63

POSITIVE LOGITS

scape

1.06

marks

0.94

ward

0.82

gra

0.80

mark

0.79

wic

0.78

 Park

0.78

estine

0.77

ic

0.77

side

0.74

Activations Density 0.025%

words related to geographic locations, specifically focusing on land or countries

references to geographical locations or place names

No Comments

No Known Activations