INDEX

Explanations

words related to software programming and development, particularly focusing on lists or views

oai_token-act-pair · gpt-3.5-turbo

occurrences of the term "List" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icago

-0.79

asio

-0.66

perty

-0.65

 gratification

-0.63

 deadliest

-0.58

rir

-0.58

ternity

-0.58

 reper

-0.56

 Wildcats

-0.55

 merry

-0.55

POSITIVE LOGITS

ening

1.27

ener

1.12

eners

1.07

ings

1.02

erv

0.95

ing

0.94

ered

0.94

uce

0.88

ett

0.88

enable

0.88

Activations Density 0.024%

words related to software programming and development, particularly focusing on lists or views

occurrences of the term "List" in various contexts

No Comments

No Known Activations