INDEX

Explanations

mentions of legal actions, charges being pressed, and legal proceedings

oai_token-act-pair · gpt-3.5-turbo

terms related to legal charges and investigations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

natureconservancy

-0.85

 Tycoon

-0.84

Planet

-0.78

Maps

-0.74

sylv

-0.72

optim

-0.72

 galaxies

-0.72

Goo

-0.71

ankind

-0.70

forums

-0.70

POSITIVE LOGITS

 levied

1.06

 penalties

1.04

 punishable

1.03

 penalty

1.02

 deterrent

1.01

 waived

1.00

 punishments

0.99

 enforced

0.97

 revoked

0.96

 payable

0.95

Activations Density 0.510%

mentions of legal actions, charges being pressed, and legal proceedings

terms related to legal charges and investigations

No Comments

No Known Activations