INDEX

Explanations

phrases related to discussions or actions within an organizational or governmental context

oai_token-act-pair · gpt-3.5-turbo

punctuation or sentence endings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Saiyan

-0.90

 Reincarnated

-0.73

¥µ

-0.73

ythm

-0.72

boro

-0.72

 Sorcerer

-0.72

tainment

-0.71

 decrypt

-0.69

 droid

-0.67

 Cipher

-0.67

POSITIVE LOGITS

Labour

0.92

Article

0.89

Canada

0.86

READ

0.85

Australia

0.82

Having

0.82

cair

0.80

Ultimately

0.80

incial

0.80

Ireland

0.80

Activations Density 0.689%

phrases related to discussions or actions within an organizational or governmental context

punctuation or sentence endings

No Comments

No Known Activations