INDEX

Explanations

technical terms related to software development or projects

oai_token-act-pair · gpt-3.5-turbo

transitional and contrasting phrases in discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

kefeller

-0.91

Report

-0.74

Officials

-0.72

Detailed

-0.70

externalActionCode

-0.68

illance

-0.67

Â¢

-0.66

SourceFile

-0.65

Investigators

-0.65

oufl

-0.65

POSITIVE LOGITS

1.28

my

1.16

 myself

1.05

 lately

1.00

 haha

0.93

 honestly

0.92

 alot

0.92

 Honestly

0.91

 Personally

0.90

Activations Density 0.376%

technical terms related to software development or projects

transitional and contrasting phrases in discourse

No Comments

No Known Activations