INDEX

Explanations

mentions of camping or camp-related activities

oai_token-act-pair · gpt-3.5-turbo

references to camping and related activities

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

lihood

-0.77

 regress

-0.69

 pudding

-0.65

 magnification

-0.65

ctive

-0.64

 nutrit

-0.62

hm

-0.62

ĸļ

-0.60

piring

-0.60

wip

-0.58

POSITIVE LOGITS

fires

1.17

ground

1.11

grounds

1.11

camp

1.08

fire

1.07

agna

1.00

 camp

0.93

agne

0.89

anas

0.89

hor

0.87

Activations Density 0.015%

mentions of camping or camp-related activities

references to camping and related activities

No Comments

No Known Activations