INDEX

Explanations

official titles and positions within government or legal contexts

oai_token-act-pair · gpt-3.5-turbo

titles and roles related to government officials and law enforcement

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

NetMessage

-0.79

 hots

-0.67

ankind

-0.64

 gamble

-0.63

urious

-0.63

iland

-0.58

 cheapest

-0.58

 trem

-0.58

rero

-0.58

 cafes

-0.58

POSITIVE LOGITS

Ake

0.86

awei

0.75

ibrarian

0.73

utenant

0.71

rees

0.71

uties

0.69

hak

0.68

arthed

0.68

 Cortex

0.66

 Kodi

0.66

Activations Density 0.152%

official titles and positions within government or legal contexts

titles and roles related to government officials and law enforcement

No Comments

No Known Activations