INDEX

Explanations

words related to authority and power

oai_token-act-pair · gpt-3.5-turbo

references to influential entities or authorities

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

 Mell

-0.72

riad

-0.71

algia

-0.71

 Dwell

-0.68

Gil

-0.67

rio

-0.67

yrinth

-0.67

00200000

-0.65

 Mour

-0.64

eor

-0.64

POSITIVE LOGITS

 powers

0.94

hell

0.90

Reviewer

0.85

 conferred

0.80

 superpower

0.78

 ashore

0.78

 Powers

0.74

 delegated

0.74

 strapped

0.71

olutions

0.70

Activations Density 0.027%

words related to authority and power

references to influential entities or authorities

No Comments

No Known Activations