INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

references to specific people, particularly those with the names "He" and "She."

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

etheless

-0.96

OPLE

-0.73

 Cummings

-0.64

 dotted

-0.64

 grav

-0.63

quo

-0.63

WAYS

-0.63

 needles

-0.63

 stiffness

-0.60

terday

-0.59

POSITIVE LOGITS

oran

1.02

ussie

0.93

chel

0.89

omer

0.89

oka

0.88

iber

0.87

itzer

0.86

mans

0.84

alf

0.84

alt

0.83

Activations Density 0.145%

names of individuals

references to specific people, particularly those with the names "He" and "She."

No Comments

No Known Activations