INDEX

Explanations

mentions of specific names or abbreviations related to government agencies or corporations

oai_token-act-pair · gpt-3.5-turbo

abbreviations and acronyms related to corporate or organizational entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ness

-0.73

bender

-0.71

ogly

-0.71

quartered

-0.71

 Cosponsors

-0.69

oug

-0.68

eworld

-0.68

--------------------------------------------------------

-0.68

ological

-0.66

*/(

-0.66

POSITIVE LOGITS

ideos

0.95

III

0.90

ascular

0.86

oodoo

0.85

iolet

0.85

ISION

0.81

ulture

0.79

antage

0.77

IRT

0.77

ortex

0.77

Activations Density 0.102%

mentions of specific names or abbreviations related to government agencies or corporations

abbreviations and acronyms related to corporate or organizational entities

No Comments

No Known Activations