INDEX

Explanations

programming code snippets containing conditions and logical operations

oai_token-act-pair · gpt-3.5-turbo

programming keywords and operations related to data handling

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ãĥ³ãĤ¸

-0.66

forth

-0.62

bourg

-0.58

 Manit

-0.58

 effortlessly

-0.58

 perspect

-0.57

SPONSORED

-0.57

 disg

-0.57

Voy

-0.56

 tremend

-0.56

POSITIVE LOGITS

==

1.52

!=

1.49

&&

1.33

==

1.27

<=

1.25

>=

1.25

===

1.22

||

1.15

eq

1.09

){

0.96

Activations Density 0.047%

programming code snippets containing conditions and logical operations

programming keywords and operations related to data handling

No Comments

No Known Activations