INDEX

Explanations

relationships like "son-in-law" or "brother-in-law."

oai_token-act-pair · gpt-3.5-turbo

phrases related to familial relationships and legal connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Ĥİ

-0.66

 Helic

-0.64

 Bullets

-0.63

 popcorn

-0.62

dur

-0.61

 calibration

-0.60

IUM

-0.60

 almonds

-0.59

 calibrated

-0.59

 durability

-0.58

POSITIVE LOGITS

turned

0.97

daughter

0.91

hood

0.90

wife

0.88

unknown

0.85

brother

0.84

christ

0.82

husband

0.81

sam

0.80

gallery

0.80

Activations Density 0.083%

relationships like "son-in-law" or "brother-in-law."

phrases related to familial relationships and legal connections

No Comments

No Known Activations