INDEX

Explanations

first-person statements discussing personal beliefs or experiences

oai_token-act-pair · gpt-3.5-turbo

first-person accounts and personal opinions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WAR

-0.67

Repeat

-0.66

 Ships

-0.65

 Repeat

-0.64

 Replacement

-0.63

 reversible

-0.63

cut

-0.62

Rib

-0.62

 ransom

-0.60

Drop

-0.60

POSITIVE LOGITS

 privileged

0.91

 responsibilities

0.82

 frequ

0.73

 acquaint

0.73

 regularly

0.71

 inherited

0.70

 intimately

0.69

 privilege

0.69

pired

0.68

 nurt

0.67

Activations Density 0.583%

first-person statements discussing personal beliefs or experiences

first-person accounts and personal opinions

No Comments

No Known Activations