INDEX

Explanations

dimensions described with measurements in millimeters

oai_token-act-pair · gpt-3.5-turbo

measurements and dimensions expressed in various units

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

éĹĺ

-0.93

Pru

-0.80

 Fargo

-0.80

ilitarian

-0.80

awaru

-0.78

ESH

-0.76

GROUND

-0.76

ãĥĦ

-0.75

EMENT

-0.74

KEN

-0.74

POSITIVE LOGITS

yz

1.21

xxxxxxxx

1.00

posed

0.93

iang

0.92

xxxx

0.91

xxx

0.88

xx

0.86

avier

0.83

iao

0.80

actly

0.79

Activations Density 0.011%

dimensions described with measurements in millimeters

measurements and dimensions expressed in various units

No Comments

No Known Activations