INDEX

Explanations

phrases related to specific events or tragedies

oai_token-act-pair · gpt-3.5-turbo

mentions of significant events and entities related to terrorism and violence

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

PROV

-0.74

Gw

-0.69

depend

-0.69

Jake

-0.65

PAX

-0.65

Balt

-0.64

LOAD

-0.62

POS

-0.62

UT

-0.62

ACTION

-0.60

POSITIVE LOGITS

 Hebdo

1.30

 Massacre

0.78

tics

0.76

acher

0.75

anca

0.74

hiba

0.73

scl

0.72

 Mansion

0.69

tsy

0.69

olini

0.69

Activations Density 0.048%

phrases related to specific events or tragedies

mentions of significant events and entities related to terrorism and violence

No Comments

No Known Activations