INDEX

Explanations

names and references to the term "Linden"

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of the name "Lind."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

-0.85

Ø©

-0.80

CLASSIFIED

-0.74

EED

-0.66

Magikarp

-0.64

NRS

-0.64

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

-0.63

ABLE

-0.63

 dism

-0.61

 inhibitors

-0.60

POSITIVE LOGITS

gren

1.26

strom

1.20

isf

1.19

say

1.12

holm

1.06

enstein

1.04

quist

1.00

enberg

0.98

wig

0.98

seys

0.97

Activations Density 0.029%

names and references to the term "Linden"

the repeated mention of the name "Lind."

No Comments

No Known Activations