INDEX

Explanations

mentions of different locations or cities where events or people are present

oai_token-act-pair · gpt-3.5-turbo

instances of the word "in."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

selves

-0.68

leness

-0.66

ESA

-0.62

isure

-0.62

eous

-0.62

ById

-0.61

lest

-0.60

thora

-0.60

Desc

-0.58

awatts

-0.58

POSITIVE LOGITS

 attendance

1.25

 touch

1.10

 contact

1.01

awe

0.99

 charge

0.98

 town

0.89

 possession

0.88

 residence

0.88

 tears

0.81

charge

0.81

Activations Density 0.142%

mentions of different locations or cities where events or people are present

instances of the word "in."

No Comments

No Known Activations