INDEX

Explanations

terms or phrases coined or used to describe certain concepts or phenomena

oai_token-act-pair · gpt-3.5-turbo

terms and definitions used in a specific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

htaking

-0.76

mits

-0.67

edient

-0.65

igators

-0.65

iencies

-0.64

Vaj

-0.63

phis

-0.62

 cooperate

-0.62

psey

-0.62

iors

-0.61

POSITIVE LOGITS

 coined

1.50

 slang

1.24

 shorthand

1.21

 synonymous

1.16

 abbre

1.09

 referring

1.07

 acronym

1.06

 uttered

1.06

 interchange

1.03

 derogatory

1.01

Activations Density 0.362%

terms or phrases coined or used to describe certain concepts or phenomena

terms and definitions used in a specific context

No Comments

No Known Activations