INDEX

Explanations

descriptions related to news events and criminal activities

oai_token-act-pair · gpt-3.5-turbo

mentions of suspects in a criminal context

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

interstitial

-0.80

soDeliveryDate

-0.78

ophon

-0.74

itivity

-0.73

 gears

-0.71

GMT

-0.70

 Catalog

-0.65

 conventions

-0.64

é¾įåĸļå£«

-0.64

umption

-0.63

POSITIVE LOGITS

 whom

0.81

 Tsarnaev

0.71

sov

0.71

emort

0.69

 Kessler

0.68

 unidentified

0.67

ENT

0.66

ryce

0.66

Kov

0.66

 Asuka

0.65

Activations Density 0.552%

descriptions related to news events and criminal activities

mentions of suspects in a criminal context

No Comments

No Known Activations