INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

proper names, particularly those of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ModLoader

-0.76

etheless

-0.74

LEASE

-0.72

 Melania

-0.68

theless

-0.67

 underwater

-0.66

 Millennials

-0.66

 Oprah

-0.65

UTERS

-0.65

 Alibaba

-0.64

POSITIVE LOGITS

zen

1.02

atz

0.96

acci

0.96

burn

0.95

utsch

0.94

inger

0.92

itz

0.92

inski

0.92

ham

0.91

owski

0.91

Activations Density 0.331%

names of individuals

proper names, particularly those of individuals

No Comments

No Known Activations