INDEX

Explanations

phrases containing numbered lists

oai_token-act-pair · gpt-3.5-turbo

phrases related to health and wellness issues

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

ahime

-0.74

 citiz

-0.69

okia

-0.68

abase

-0.66

ijah

-0.66

ufact

-0.65

iage

-0.63

 carriage

-0.61

culosis

-0.60

nesday

-0.58

POSITIVE LOGITS

SPONSORED

1.04

Such

0.99

ADVERTISEMENT

0.96

Scroll

0.96

METHOD

0.95

Sounds

0.91

Ultimately

0.91

Thus

0.88

Again

0.87

Until

0.85

Activations Density 0.775%

phrases containing numbered lists

phrases related to health and wellness issues

No Comments

No Known Activations