INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

mentions of individuals or characters associated with specific names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

eering

-0.96

ably

-0.86

OPLE

-0.85

IBLE

-0.78

ÙĦ

-0.74

Ø¯

-0.74

++++++++++++++++

-0.74

urdue

-0.71

ually

-0.67

antly

-0.66

POSITIVE LOGITS

Ny

1.13

quist

0.87

heter

0.85

borg

0.80

ota

0.78

comed

0.77

yk

0.73

Ey

0.73

seys

0.72

ody

0.72

Activations Density 0.007%

proper nouns

mentions of individuals or characters associated with specific names

No Comments

No Known Activations