INDEX

Explanations

phrases related to making choices or comparisons

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

prepositions and their usage in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

arta

-0.78

Synopsis

-0.76

lys

-0.72

laughter

-0.67

CVE

-0.66

cies

-0.66

arrell

-0.65

urnal

-0.64

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

-0.63

imbabwe

-0.63

POSITIVE LOGITS

 relying

1.44

 using

1.35

 having

1.27

 opting

1.24

 buying

1.24

 installing

1.23

 putting

1.20

 preferring

1.20

 needing

1.17

 adding

1.16

Activations Density 0.448%

phrases related to making choices or comparisons

prepositions and their usage in context

No Comments

No Known Activations