INDEX

Explanations

phrases related to legal actions or disputes

oai_token-act-pair · gpt-3.5-turbo

repeated conjunctions that indicate lists or connections between ideas

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

onica

-0.81

ahime

-0.76

tick

-0.72

roller

-0.70

iatus

-0.66

agog

-0.64

ibble

-0.64

buster

-0.64

rollers

-0.63

Times

-0.63

POSITIVE LOGITS

 furthermore

1.32

 consequently

1.25

 secondly

1.24

 moreover

1.23

 additionally

1.22

 thence

1.10

 also

1.08

 hence

1.06

 therefore

1.05

 thereby

1.03

Activations Density 0.256%

phrases related to legal actions or disputes

repeated conjunctions that indicate lists or connections between ideas

No Comments

No Known Activations