INDEX

Explanations

texts related to product descriptions or updates

oai_token-act-pair · gpt-3.5-turbo

references to products and their placements

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

laus

-0.75

aft

-0.70

 Brother

-0.69

asons

-0.68

CLASSIFIED

-0.68

arning

-0.62

 Shades

-0.62

apo

-0.61

 millenn

-0.61

trop

-0.61

POSITIVE LOGITS

ivity

1.31

ively

1.09

ivities

0.94

iveness

0.89

 packaging

0.85

Hunt

0.80

kit

0.75

rador

0.74

Products

0.71

ournals

0.69

Activations Density 0.023%

texts related to product descriptions or updates

references to products and their placements

No Comments

No Known Activations