INDEX

Explanations

proper nouns

oai_token-act-pair · gpt-3.5-turbo

usage of punctuation and structural elements in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

sburg

-0.68

ertodd

-0.66

iquette

-0.66

ei

-0.65

STON

-0.63

acters

-0.62

irie

-0.62

bucks

-0.62

riages

-0.60

ths

-0.60

POSITIVE LOGITS

 which

1.52

 whose

1.52

whose

1.41

which

1.36

 wherein

1.23

 whereby

1.15

 where

1.12

 whom

1.11

 whence

1.07

who

1.03

Activations Density 0.483%

proper nouns

usage of punctuation and structural elements in the text

No Comments

No Known Activations