INDEX

Explanations

the word "bond" followed by a number indicating a level of significance or importance

oai_token-act-pair · gpt-3.5-turbo

references to financial instruments or obligations related to bonds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

upiter

-0.86

ãĤ¦ãĤ¹

-0.79

å¤©

-0.74

stasy

-0.74

resents

-0.72

ç¥ŀ

-0.71

ãĥ³ãĤ¸

-0.71

ordan

-0.70

ãĥ´ãĤ¡

-0.69

oppers

-0.68

POSITIVE LOGITS

 bond

1.04

 bonds

1.01

 bonded

0.98

holders

0.94

 bonding

0.86

 Bonds

0.77

Connector

0.75

 Vaugh

0.75

holder

0.73

master

0.72

Activations Density 0.012%

the word "bond" followed by a number indicating a level of significance or importance

references to financial instruments or obligations related to bonds

No Comments

No Known Activations