INDEX

Explanations

words related to legal actions being taken

oai_token-act-pair · gpt-3.5-turbo

terms related to legal appeals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ñĥ

-0.72

fters

-0.72

ifa

-0.71

 Rocks

-0.70

âĹ¼

-0.69

 Grad

-0.67

Benz

-0.66

Poc

-0.66

 Benz

-0.65

aughtered

-0.65

POSITIVE LOGITS

ĸļ

0.96

 parole

0.85

 appeal

0.84

 appeals

0.82

 rejection

0.77

ishment

0.76

 plea

0.74

 pend

0.73

duction

0.72

 hearings

0.72

Activations Density 0.012%

words related to legal actions being taken

terms related to legal appeals

No Comments

No Known Activations