INDEX

Explanations

mentions of the name "Antonio"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Antonio"

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

lasses

-1.02

cipled

-0.78

nda

-0.76

ħ

-0.76

glers

-0.72

orders

-0.69

bles

-0.69

srf

-0.67

cribed

-0.66

 fixme

-0.66

POSITIVE LOGITS

 Spurs

0.95

omy

0.81

atoes

0.76

ivo

0.76

quit

0.75

apolis

0.75

 Antonio

0.74

oise

0.74

iso

0.73

aceae

0.73

Activations Density 0.015%

mentions of the name "Antonio"

mentions of the name "Antonio"

No Comments

No Known Activations