INDEX

Explanations

terms related to having a similar mindset or attitude

oai_token-act-pair · gpt-3.5-turbo

instances of the term "open-minded" 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 @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 Hemp

-0.62

 morphine

-0.60

ARDS

-0.60

atro

-0.60

IDS

-0.59

ILA

-0.59

 reinforcing

-0.58

ULT

-0.58

ODE

-0.58

atern

-0.58

POSITIVE LOGITS

minded

1.37

 minded

1.28

edly

1.13

llor

0.99

ness

0.95

edIn

0.95

emouth

0.94

quartered

0.92

cipled

0.88

iciary

0.85

Activations Density 0.016%

terms related to having a similar mindset or attitude

instances of the term "open-minded" in various contexts

No Comments

No Known Activations