INDEX

Explanations

legal terms or phrases

oai_token-act-pair · gpt-3.5-turbo

terms and phrases related to legal concepts and legal obligations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Seasons

-0.81

mble

-0.72

 Roses

-0.68

pread

-0.68

 Velocity

-0.68

Ran

-0.68

 Lans

-0.67

vae

-0.66

 Tycoon

-0.66

 Garfield

-0.65

POSITIVE LOGITS

 speaking

0.87

 enforce

0.84

 exting

0.84

 wedd

0.79

ãĤ´ãĥ³

0.79

 sanctioned

0.78

 obliged

0.78

 mandated

0.77

 obligated

0.77

 ratified

0.76

Activations Density 0.010%

legal terms or phrases

terms and phrases related to legal concepts and legal obligations

No Comments

No Known Activations