INDEX

Explanations

words related to technology and actions taken or not taken in a specific context

oai_token-act-pair · gpt-3.5-turbo

instances of actions or events that indicate failure or error

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 suspic

-0.56

views

-0.51

WORK

-0.51

earned

-0.49

 Hammond

-0.49

forts

-0.49

ISTORY

-0.48

redits

-0.48

interstitial

-0.48

 prejudice

-0.47

POSITIVE LOGITS

 Leilan

0.83

soDeliveryDate

0.62

[|

0.58

 pandemonium

0.57

 Marketable

0.56

 Cthulhu

0.54

ãĥīãĥ©ãĤ´ãĥ³

0.54

 Seraph

0.53

 Andromeda

0.52

 Neptune

0.51

Activations Density 1.516%

words related to technology and actions taken or not taken in a specific context

instances of actions or events that indicate failure or error

No Comments

No Known Activations