INDEX

Explanations

words related to geographical locations or organizations, especially those ending with "hire."

oai_token-act-pair · gpt-3.5-turbo

references to geographical locations, specifically counties and regions

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

acs

-0.83

aganda

-0.82

ihilation

-0.80

aturation

-0.78

inventoryQuantity

-0.76

ongyang

-0.76

onym

-0.76

amacare

-0.76

bern

-0.75

gotten

-0.75

POSITIVE LOGITS

hire

1.26

 Hath

1.03

shire

0.97

 Regiment

0.91

 Borough

0.89

 Railway

0.85

 Sussex

0.81

 Crown

0.81

 Rover

0.79

 County

0.78

Activations Density 0.019%

words related to geographical locations or organizations, especially those ending with "hire."

references to geographical locations, specifically counties and regions

No Comments

No Known Activations