INDEX

Explanations

phrases related to benefits, advantages, and giving someone the benefit of the doubt

oai_token-act-pair · gpt-3.5-turbo

phrases that denote benefits or advantages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

mson

-0.77

 delinquent

-0.74

soDeliveryDate

-0.69

waters

-0.65

issy

-0.65

ATED

-0.64

idelines

-0.64

Ã³n

-0.64

fuck

-0.62

ohm

-0.61

POSITIVE LOGITS

 outweigh

0.94

 hindsight

0.86

 flexibility

0.85

 plentiful

0.83

 outwe

0.82

 conferred

0.81

 riches

0.80

 benefits

0.78

 exporting

0.74

 afforded

0.73

Activations Density 0.297%

phrases related to benefits, advantages, and giving someone the benefit of the doubt

phrases that denote benefits or advantages

No Comments

No Known Activations