INDEX

Explanations

mentions or references to government officials or governance-related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to governance and political authority

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

 crane

-0.74

 guidance

-0.67

 tongue

-0.66

 shroud

-0.62

 grip

-0.61

Cum

-0.61

ISM

-0.60

 deduction

-0.60

 Archangel

-0.59

 hiking

-0.59

POSITIVE LOGITS

ments

1.73

ations

1.33

ances

1.30

ors

1.27

ences

1.26

ings

1.24

ents

1.24

ency

1.23

ance

1.21

ions

1.20

Activations Density 0.086%

mentions or references to government officials or governance-related terms

terms related to governance and political authority

No Comments

No Known Activations