INDEX

Explanations

words related to engraving or inscribing

oai_token-act-pair · gpt-3.5-turbo

terms related to engraving and inscriptions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

meta

-0.86

pmwiki

-0.84

 assets

-0.75

 Meta

-0.71

NET

-0.68

 SWAT

-0.68

Meta

-0.68

EStreamFrame

-0.67

fox

-0.67

 Javascript

-0.67

POSITIVE LOGITS

 engraved

3.02

 etched

2.59

 inscribed

2.49

 enshr

2.20

 inscription

1.96

 plaque

1.86

 imprint

1.77

eng

1.75

 commemor

1.55

 ingrained

1.42

Activations Density 0.050%

words related to engraving or inscribing

terms related to engraving and inscriptions

No Comments

No Known Activations