INDEX

Explanations

text related to comments and discussions

oai_token-act-pair · gpt-3.5-turbo

variations of the word "comment" and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

icz

-0.74

 Sinai

-0.73

lay

-0.65

 Newport

-0.64

 Metatron

-0.62

YP

-0.62

duc

-0.61

 Lansing

-0.61

 abduction

-0.60

 Eston

-0.60

POSITIVE LOGITS

ariat

1.27

aries

1.22

ators

1.00

ature

0.94

arial

0.93

 sections

0.84

atively

0.83

area

0.82

ator

0.82

 threads

0.81

Activations Density 0.059%

text related to comments and discussions

variations of the word "comment" and related terms

No Comments

No Known Activations