INDEX

Explanations

words related to computer programming, specifically involving the programming language 'C'

oai_token-act-pair · gpt-3.5-turbo

recurring mentions or references to the letter 'C'

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

 Yamaha

-0.72

ãĥĦ

-0.70

 Tinder

-0.68

ItemTracker

-0.66

Magikarp

-0.66

hof

-0.66

 absor

-0.64

 belie

-0.63

Tup

-0.63

 Wrestle

-0.62

POSITIVE LOGITS

overed

1.16

URRENT

1.13

ancel

1.08

isco

1.08

argo

1.07

olly

1.06

urses

1.06

ologne

1.05

ursed

1.04

rouch

1.03

Activations Density 0.050%

words related to computer programming, specifically involving the programming language 'C'

recurring mentions or references to the letter 'C'

No Comments

No Known Activations