INDEX

Explanations

related to instances of causality or things that come before other things

oai_token-act-pair · gpt-3.5-turbo

terms related to causation and predictive relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

aneers

-0.91

arro

-0.79

quished

-0.79

enstein

-0.77

atan

-0.77

estern

-0.77

tower

-0.76

oise

-0.76

ÄŁ

-0.76

ffen

-0.75

POSITIVE LOGITS

 predictive

0.91

 precursor

0.85

 indicative

0.84

 indicators

0.83

interstitial

0.79

 satell

0.78

hetically

0.78

 opio

0.76

 correlate

0.76

 markers

0.75

Activations Density 0.024%

related to instances of causality or things that come before other things

terms related to causation and predictive relationships

No Comments

No Known Activations