INDEX

Explanations

keywords related to legal actions, particularly defamation lawsuits

oai_token-act-pair · gpt-3.5-turbo

terms related to defamation and false allegations

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

ebus

-0.95

foreseen

-0.77

 guiActiveUnfocused

-0.75

arta

-0.69

hedral

-0.68

stice

-0.67

asio

-0.65

rossover

-0.65

rison

-0.65

leep

-0.64

POSITIVE LOGITS

 baseless

0.92

 allegations

0.89

 unfounded

0.89

 discredited

0.87

 allegation

0.86

 slander

0.84

 debunked

0.84

 untrue

0.83

 debunk

0.81

 accusations

0.80

Activations Density 0.041%

keywords related to legal actions, particularly defamation lawsuits

terms related to defamation and false allegations

No Comments

No Known Activations