INDEX

Explanations

personal or location names, possibly related to politics and military

oai_token-act-pair · gpt-3.5-turbo

terms related to specific measurements or instances of numerical significance

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 stump

-0.70

Priv

-0.67

 judgement

-0.66

pse

-0.66

headers

-0.66

venants

-0.62

soDeliveryDate

-0.62

 backlog

-0.61

ĸļ

-0.60

 elevation

-0.60

POSITIVE LOGITS

ruary

1.03

enza

0.86

agy

0.86

illet

0.84

acci

0.82

cus

0.81

tein

0.81

nir

0.80

igure

0.79

ancial

0.78

Activations Density 0.242%

personal or location names, possibly related to politics and military

terms related to specific measurements or instances of numerical significance

No Comments

No Known Activations