INDEX

Explanations

words related to biography or historical narratives

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

cffffcc

-0.68

Pwr

-0.60

lycer

-0.55

Ń·

-0.52

§

-0.51

wcsstore

-0.50

cedented

-0.49

ForgeModLoader

-0.49

ivers

-0.48

atters

-0.48

POSITIVE LOGITS

 workings

0.59

 Fitz

0.56

 versus

0.54

liest

0.52

 misconceptions

0.51

 transpired

0.51

 unfold

0.50

Topics

0.49

perty

0.47

 withd

0.47

Activations Density 1.301%

words related to biography or historical narratives

No Comments

No Known Activations