INDEX

Explanations

references to financial institutions or economic concepts

oai_token-act-pair · gpt-3.5-turbo

words related to expertise and knowledge in a specific field, particularly that which emphasizes taste and quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

angering

-0.87

enn

-0.83

odd

-0.78

 ILCS

-0.77

emonic

-0.72

ennett

-0.71

idious

-0.70

soDeliveryDate

-0.70

é¾įå

-0.68

incible

-0.67

POSITIVE LOGITS

lette

1.13

rers

1.04

rer

1.01

tto

0.97

zza

0.90

udo

0.89

lete

0.85

tta

0.84

ppe

0.83

tics

0.81

Activations Density 0.039%

references to financial institutions or economic concepts

words related to expertise and knowledge in a specific field, particularly that which emphasizes taste and quality

No Comments

No Known Activations