INDEX

Explanations

dates and events related to terrorist attacks

oai_token-act-pair · gpt-3.5-turbo

references to the September 11 attacks and related events

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

æĢ

-0.74

 Seller

-0.74

 Tsuk

-0.69

 Panasonic

-0.69

Featured

-0.68

Farm

-0.68

 Marketable

-0.67

é¾įå

-0.67

Avg

-0.66

 Somew

-0.66

POSITIVE LOGITS

 terror

0.96

 hijacked

0.94

hij

0.94

ghazi

0.91

 bombing

0.90

 bombings

0.87

wre

0.84

 assassination

0.84

 bombers

0.82

dinand

0.80

Activations Density 0.103%

dates and events related to terrorist attacks

references to the September 11 attacks and related events

No Comments

No Known Activations