INDEX

Explanations

concluding statements and explanations

oai_token-act-pair · gpt-3.5-turbo

elements of recommendations or evaluations related to products or experiences

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

 freel

-0.87

 migrant

-0.84

 retweet

-0.83

 congreg

-0.82

 volunteer

-0.82

 betting

-0.81

 divest

-0.80

 interpre

-0.80

 amnesty

-0.80

 volunteering

-0.80

POSITIVE LOGITS

Features

1.87

Pros

1.70

Rated

1.68

Product

1.66

Hardware

1.66

Spec

1.66

Design

1.63

Manufact

1.61

Installation

1.58

Price

1.55

Activations Density 0.253%

concluding statements and explanations

elements of recommendations or evaluations related to products or experiences

No Comments

No Known Activations