INDEX

Explanations

contractions of negations, such as "don't" or "doesn't"

oai_token-act-pair · gpt-3.5-turbo

negations or phrases that indicate 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 @ 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

Negative Logits

çĶŁ

-0.71

PDATE

-0.68

itiz

-0.68

 Laun

-0.66

jected

-0.65

 Opportun

-0.65

 è£ıè

-0.65

stre

-0.64

 unforeseen

-0.64

estern

-0.63

POSITIVE LOGITS

 necessarily

1.28

 seem

1.23

 belong

1.14

 deserve

1.12

 condone

1.12

 discriminate

1.10

 exist

1.09

 intend

1.09

 appear

1.07

 hesitate

1.04

Activations Density 0.125%

contractions of negations, such as "don't" or "doesn't"

negations or phrases that indicate absence or denial

No Known Activations