INDEX

Explanations

names of various individuals

oai_token-act-pair · gpt-3.5-turbo

proper names, particularly those of people

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

 hindsight

-0.74

PDATE

-0.73

 looph

-0.69

translation

-0.69

ISION

-0.67

 Flavoring

-0.67

yip

-0.67

ModLoader

-0.66

ãĤŃ

-0.64

 Pradesh

-0.64

POSITIVE LOGITS

 herself

1.00

deen

0.82

ova

0.78

 nursing

0.75

 bikini

0.74

shaw

0.74

oun

0.73

 miscar

0.73

bors

0.73

 Nursing

0.73

Activations Density 0.273%

names of various individuals

proper names, particularly those of people

No Comments

No Known Activations