INDEX

Explanations

phrases related to rejecting, getting rid of, or discarding something

oai_token-act-pair · gpt-3.5-turbo

phrases centered around the concept of "throwing out" or discarding

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

APH

-0.80

ÃŁ

-0.77

ND

-0.76

CLA

-0.73

SET

-0.71

Marginal

-0.69

going

-0.68

achine

-0.68

Wem

-0.67

Ë

-0.67

POSITIVE LOGITS

 overboard

0.91

 tant

0.80

 insult

0.71

 blame

0.70

 grenades

0.68

 Tuls

0.67

poon

0.62

 Shal

0.62

rav

0.62

 grenade

0.62

Activations Density 0.110%

phrases related to rejecting, getting rid of, or discarding something

phrases centered around the concept of "throwing out" or discarding

No Comments

No Known Activations