INDEX

Explanations

measurements related to precision, such as intervals and accuracies

oai_token-act-pair · gpt-3.5-turbo

phrases related to precision and comparison

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

 Rodham

-0.75

 relapse

-0.72

vernment

-0.71

 vandal

-0.68

 Wednesday

-0.68

 playbook

-0.67

endar

-0.67

Wednesday

-0.67

 delinquent

-0.66

 Weekly

-0.64

POSITIVE LOGITS

 advantages

1.11

 disadvantages

1.04

 advantageous

1.04

advant

1.04

 drawback

1.00

 disadvantage

0.99

 advantage

0.98

 eliminates

0.91

 versatility

0.89

 enables

0.85

Activations Density 0.551%

measurements related to precision, such as intervals and accuracies

phrases related to precision and comparison

No Comments

No Known Activations