INDEX

Explanations

words related to written or spoken communication

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of "diocese."

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

ãĤ¤ãĥĪ

-0.80

ãģĨ

-0.80

 Seah

-0.76

manship

-0.75

 spare

-0.75

 totality

-0.71

INGS

-0.70

éĹĺ

-0.70

HCR

-0.69

å§«

-0.68

POSITIVE LOGITS

abol

1.26

ocese

1.22

urnal

1.21

abolic

1.18

agon

1.06

agram

0.95

utsch

0.94

atal

0.89

aper

0.88

ablo

0.88

Activations Density 0.010%

words related to written or spoken communication

terms related to the concept of "diocese."

No Comments

No Known Activations