INDEX

Explanations

keywords or phrases related to lists

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "list" 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

perty

-0.71

 merry

-0.64

wav

-0.64

 Aber

-0.64

 Thames

-0.62

icago

-0.60

displayText

-0.59

 sailing

-0.58

 seas

-0.58

ILLE

-0.57

POSITIVE LOGITS

ening

1.42

ener

1.25

eners

1.17

ing

1.07

ened

1.03

erv

1.02

enf

0.98

ensen

0.91

abet

0.90

ings

0.89

Activations Density 0.020%

keywords or phrases related to lists

occurrences of the word "list" in various contexts

No Comments

No Known Activations