INDEX

Explanations

mentions of military ranks and related terms

oai_token-act-pair · gpt-3.5-turbo

references to cadets

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Borders

-0.67

 Fargo

-0.63

 pity

-0.61

 fertility

-0.58

 TABLE

-0.57

 nerv

-0.57

Lov

-0.57

ãĤ®

-0.56

LY

-0.56

 misery

-0.55

POSITIVE LOGITS

illac

1.19

enza

1.17

estones

1.14

eter

1.10

ency

1.06

enary

1.04

uce

1.04

eters

1.03

leton

1.01

ulla

0.99

Activations Density 0.038%

mentions of military ranks and related terms

references to cadets

No Comments

No Known Activations