INDEX

Explanations

mentions of slot-related activities or references

oai_token-act-pair · gpt-3.5-turbo

mentions of various types of slots

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

omorphic

-0.69

ĨĴ

-0.69

externalActionCode

-0.64

omen

-0.63

 Wheat

-0.60

Pyr

-0.60

harm

-0.57

é»Ĵ

-0.57

Psy

-0.56

 WARN

-0.56

POSITIVE LOGITS

tery

1.01

 slots

1.00

Slot

0.98

 slot

0.98

ting

0.94

ioned

0.88

ular

0.88

ularity

0.83

lot

0.82

slot

0.79

Activations Density 0.010%

mentions of slot-related activities or references

mentions of various types of slots

No Comments

No Known Activations