INDEX

Explanations

contractions indicating a negation or absence

oai_token-act-pair · gpt-3.5-turbo

contractions indicating absence or denial

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

DIT

-0.62

CRIP

-0.60

 searches

-0.58

 Polic

-0.57

APH

-0.57

 Picture

-0.56

RTX

-0.56

Site

-0.56

Pit

-0.55

 mock

-0.55

POSITIVE LOGITS

 been

0.96

yet

0.92

gotten

0.91

 gotten

0.90

been

0.83

theless

0.83

 bothered

0.82

iban

0.82

 hesitated

0.81

yet

0.81

Activations Density 0.019%

contractions indicating a negation or absence

contractions indicating absence or denial

No Comments

No Known Activations