INDEX

Explanations

words related to waste or unwanted items

oai_token-act-pair · gpt-3.5-turbo

words or terms related to waste and recycling

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

 Byrd

-0.64

 pronounced

-0.64

 diplom

-0.63

 endowed

-0.62

 princ

-0.62

 Xavier

-0.61

 encount

-0.61

BILITY

-0.61

 accomp

-0.61

\'

-0.60

POSITIVE LOGITS

 Products

0.86

grass

0.86

Stream

0.82

ulent

0.81

olit

0.80

 Seeds

0.80

 Foods

0.80

haus

0.79

glass

0.77

heimer

0.76

Activations Density 0.305%

words related to waste or unwanted items

words or terms related to waste and recycling

No Comments

No Known Activations