INDEX

Explanations

phrases related to the concept of "least" or things of minimal preference

oai_token-act-pair · gpt-3.5-turbo

phrases that include the concept of "least" or "least liked."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

raltar

-0.82

ses

-0.81

çīĪ

-0.70

clerosis

-0.67

andise

-0.67

 Reborn

-0.65

stru

-0.64

WithNo

-0.64

pez

-0.64

zie

-0.63

POSITIVE LOGITS

 intrusive

0.94

 amount

0.93

 objectionable

0.88

bit

0.86

 restrictive

0.81

 detectable

0.81

 imaginable

0.80

ening

0.77

 expensive

0.75

 risky

0.74

Activations Density 0.019%

phrases related to the concept of "least" or things of minimal preference

phrases that include the concept of "least" or "least liked."

No Comments

No Known Activations