INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

articles indicating a person's identity or description

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

soType

-0.82

ovie

-0.81

inventoryQuantity

-0.78

cation

-0.74

Eye

-0.69

Alien

-0.69

APD

-0.68

ombies

-0.68

osity

-0.68

orders

-0.67

POSITIVE LOGITS

 graduate

1.09

 devout

1.06

 lifelong

1.03

 freelance

0.96

 talented

0.95

 retired

0.95

 native

0.93

 seasoned

0.93

 prolific

0.92

 former

0.91

Activations Density 0.129%

proper nouns

articles indicating a person's identity or description

No Comments

No Known Activations