INDEX

Explanations

mentions of "and" along with other words or phrases in the context

oai_token-act-pair · gpt-3.5-turbo

conjunctions and phrases indicating associations or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

edia

-0.82

oker

-0.79

uve

-0.75

=>

-0.73

wrap

-0.70

ļéĨĴ

-0.70

 Pigs

-0.69

 Herrera

-0.68

join

-0.68

wolf

-0.67

POSITIVE LOGITS

 perm

0.94

 idiosyncr

0.93

 combinations

0.90

 accol

0.90

 enthus

0.90

 configurations

0.87

 acron

0.86

 intric

0.86

 nuance

0.84

 assorted

0.83

Activations Density 0.203%

mentions of "and" along with other words or phrases in the context

conjunctions and phrases indicating associations or connections

No Comments

No Known Activations