INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "listed" in various contexts

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

qua

-0.88

issance

-0.85

isoft

-0.71

rir

-0.68

omen

-0.68

Gaw

-0.64

squ

-0.64

irth

-0.64

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.64

 satur

-0.63

POSITIVE LOGITS

 listing

0.95

 listings

0.91

 Seller

0.84

erv

0.81

onyms

0.77

enance

0.74

 keywords

0.73

dated

0.73

peed

0.71

worthy

0.68

Activations Density 0.024%

proper nouns or names

occurrences of the word "listed" in various contexts

No Comments

No Known Activations