INDEX

Explanations

phrases related to legal terms and discussions

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a continuation or elaboration of a thought

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

robe

-0.73

cell

-0.63

ety

-0.63

ãĥ¥

-0.63

ahu

-0.62

uci

-0.60

UF

-0.59

boro

-0.58

rack

-0.58

apsed

-0.57

POSITIVE LOGITS

 namely

1.33

 albeit

1.26

 however

1.07

 though

1.02

 although

1.01

 insofar

1.01

 according

0.96

 whereby

0.95

huh

0.93

 including

0.92

Activations Density 0.689%

phrases related to legal terms and discussions

phrases that indicate a continuation or elaboration of a thought

No Comments

No Known Activations