INDEX

Explanations

words related to clothing or attire

oai_token-act-pair · gpt-3.5-turbo

the letter "d" in various contexts and forms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Forth

-0.75

 Decay

-0.65

 questioning

-0.61

 Pyramid

-0.59

 slack

-0.59

 reclaimed

-0.59

Yuk

-0.58

 Favor

-0.58

 momentum

-0.58

 Aval

-0.58

POSITIVE LOGITS

ummies

1.31

renched

1.30

itto

1.30

ildo

1.21

azed

1.19

ashing

1.19

ividual

1.17

rugged

1.15

ashes

1.14

abbling

1.13

Activations Density 0.019%

words related to clothing or attire

the letter "d" in various contexts and forms

No Comments

No Known Activations