INDEX

Explanations

mentions of names or pronouns 'Jen'

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Jen" and related variations

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

tarians

-0.70

Interstitial

-0.69

 IMAGES

-0.66

milo

-0.64

 disperse

-0.64

Reloaded

-0.64

oppable

-0.64

ngth

-0.63

 reconc

-0.63

llor

-0.62

POSITIVE LOGITS

jen

1.05

kins

1.05

issance

1.04

erk

1.00

kees

0.98

cil

0.96

esis

0.94

kel

0.93

elle

0.92

Jen

0.90

Activations Density 0.016%

mentions of names or pronouns 'Jen'

mentions of the name "Jen" and related variations

No Comments

No Known Activations