INDEX

Explanations

references to profits and profit-related terms

oai_token-act-pair · gpt-3.5-turbo

mentions of profit-related concepts

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

thia

-0.65

chairs

-0.64

ocally

-0.63

gel

-0.61

stanbul

-0.61

cling

-0.60

 moss

-0.60

IPS

-0.60

 womb

-0.60

confirmed

-0.59

POSITIVE LOGITS

 margins

1.14

 margin

1.06

 profit

0.98

 profits

0.89

ulent

0.86

 motive

0.85

ably

0.83

 Profit

0.83

 earnings

0.77

 ventures

0.72

Activations Density 0.026%

references to profits and profit-related terms

mentions of profit-related concepts

No Comments

No Known Activations