INDEX

Explanations

references to a particular name 'Lind'

oai_token-act-pair · gpt-3.5-turbo

instances of the name "Lind" 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

OPLE

-0.81

Ø©

-0.75

 diaper

-0.63

 inhibitors

-0.63

FTA

-0.61

================================================================

-0.61

ABLE

-0.60

 dism

-0.60

================================

-0.59

 diapers

-0.57

POSITIVE LOGITS

strom

1.25

gren

1.24

isf

1.16

say

1.14

holm

1.08

quist

1.06

amar

1.05

ahl

1.05

enberg

1.04

orf

1.04

Activations Density 0.042%

references to a particular name 'Lind'

instances of the name "Lind" in various contexts

No Comments

No Known Activations