INDEX

Explanations

phrases related to expressions of opinions or perspectives

oai_token-act-pair · gpt-3.5-turbo

instances of a specific character or symbol

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

IFrame

Link

Negative Logits

 organisers

-0.75

 clitor

-0.74

 unborn

-0.72

 scissors

-0.71

 apes

-0.71

 virginity

-0.70

 sails

-0.67

 womb

-0.66

bun

-0.66

 tyres

-0.66

POSITIVE LOGITS

ï¸ı

1.25

âĶĢâĶĢ

1.12

conom

0.98

----------------------------------------------------------------

0.94

ł

0.93

âĶĢâĶĢâĶĢâĶĢ

0.87

jj

0.85

HUD

0.84

ï¸

0.83

fter

0.82

Activations Density 0.201%

phrases related to expressions of opinions or perspectives

instances of a specific character or symbol

No Known Activations