INDEX

Explanations

words related to measurement or assessment

oai_token-act-pair · gpt-3.5-turbo

the term "indicator" and its related forms in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

frey

-0.96

zanne

-0.79

atche

-0.77

awar

-0.77

ledge

-0.71

zens

-0.69

ITT

-0.68

nee

-0.67

nan

-0.66

artney

-0.65

POSITIVE LOGITS

 indicators

1.37

 indicator

1.30

 indication

0.89

 markers

0.88

 indic

0.81

 indications

0.81

 Signs

0.81

 gauge

0.76

icators

0.74

 deterrent

0.74

Activations Density 0.009%

words related to measurement or assessment

the term "indicator" and its related forms in various contexts

No Comments

No Known Activations