INDEX

Explanations

terms related to technology companies and projects

oai_token-act-pair · gpt-3.5-turbo

language related to charitable contributions and nonprofit organizations

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

lying

-0.68

schild

-0.64

DonaldTrump

-0.60

alions

-0.58

 corros

-0.58

)]

-0.56

isky

-0.56

mbudsman

-0.56

cli

-0.56

threat

-0.56

POSITIVE LOGITS

 Comic

0.71

 Anime

0.65

 somew

0.65

 themed

0.65

sci

0.63

 Robot

0.63

 backstage

0.61

 shutter

0.61

Gamer

0.60

 Nebula

0.60

Activations Density 1.855%

terms related to technology companies and projects

language related to charitable contributions and nonprofit organizations

No Comments

No Known Activations