INDEX

Explanations

phrases related to reporting news events

oai_token-act-pair · gpt-3.5-turbo

statements related to incidents and their consequences

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

olkien

-0.69

ilibrium

-0.65

 philosophers

-0.65

 theoret

-0.63

iosyncr

-0.63

 Slate

-0.62

 theorist

-0.62

omics

-0.59

roleum

-0.58

 Keynes

-0.58

POSITIVE LOGITS

sic

0.90

 RCMP

0.84

police

0.84

Prosecut

0.83

Alert

0.81

Police

0.81

Investigators

0.79

 custody

0.78

Emergency

0.75

Charges

0.75

Activations Density 2.569%

phrases related to reporting news events

statements related to incidents and their consequences

No Comments

No Known Activations