INDEX

Explanations

legal terms and mentions of legal actions

oai_token-act-pair · gpt-3.5-turbo

instances of high-stakes situations or conditions that involve legal or ethical violations

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

¬¼

-0.60

iple

-0.59

ety

-0.55

ocl

-0.53

uber

-0.51

cel

-0.50

reprene

-0.48

odes

-0.48

uto

-0.47

uit

-0.47

POSITIVE LOGITS

 albeit

1.05

 namely

1.02

 although

0.91

 whereas

0.87

 including

0.86

 which

0.82

 though

0.81

 regardless

0.77

but

0.76

 wherein

0.76

Activations Density 0.743%

legal terms and mentions of legal actions

instances of high-stakes situations or conditions that involve legal or ethical violations

No Comments

No Known Activations