INDEX

Explanations

word parts related to the fictional character "Aragorn" from "The Lord of the Rings."

oai_token-act-pair · gpt-3.5-turbo

the word "ag" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 Parenthood

-0.71

 Hurricanes

-0.70

 defendant

-0.70

 numbered

-0.63

 comma

-0.62

 stead

-0.62

 plaintiff

-0.60

 fossil

-0.59

 hurry

-0.58

 Commonwealth

-0.58

POSITIVE LOGITS

agging

1.07

gers

1.05

reement

1.05

raf

1.04

roup

1.03

gress

1.03

ogo

1.03

aming

1.02

uild

1.01

reements

1.00

Activations Density 0.019%

word parts related to the fictional character "Aragorn" from "The Lord of the Rings."

the word "ag" in various contexts

No Comments

No Known Activations