INDEX

Explanations

proper nouns related to people's names

oai_token-act-pair · gpt-3.5-turbo

repeated mentions of specific names, particularly "Jacobs" and "Brun."

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

mble

-0.95

aceutical

-0.85

atively

-0.73

ivid

-0.71

ocally

-0.69

raq

-0.67

umin

-0.67

ograp

-0.67

ãĥī

-0.66

 Warfare

-0.66

POSITIVE LOGITS

 Brun

0.82

ton

0.76

tones

0.70

hou

0.69

ernaut

0.69

son

0.69

aign

0.68

 Jacobs

0.68

mand

0.68

ette

0.68

Activations Density 0.028%

proper nouns related to people's names

repeated mentions of specific names, particularly "Jacobs" and "Brun."

No Comments

No Known Activations