INDEX

Explanations

years from the 1950s

oai_token-act-pair · gpt-3.5-turbo

specific years, particularly those in the mid-20th century

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hed

-0.83

EStreamFrame

-0.76

ithe

-0.71

resso

-0.70

parency

-0.69

tro

-0.67

inventoryQuantity

-0.66

hes

-0.65

afort

-0.64

itivity

-0.63

POSITIVE LOGITS

å¹

0.75

 Eisenhower

0.74

-'

0.73

0.67

chev

0.66

çļ

0.66

 Truman

0.66

 Bomber

0.64

Activations Density 0.022%

years from the 1950s

specific years, particularly those in the mid-20th century

No Comments

No Known Activations