INDEX

Explanations

occurrences of numerical sequences starting with the number "two"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "two."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

nect

-0.66

HY

-0.64

lez

-0.64

 srfAttach

-0.63

CLE

-0.62

vale

-0.62

ĺħ

-0.61

osate

-0.61

rawdownloadcloneembedreportprint

-0.60

 Changed

-0.60

POSITIVE LOGITS

 paragraphs

1.00

teen

0.96

 thirds

0.94

teenth

0.91

 weeks

0.90

 iterations

0.89

 months

0.88

 digits

0.87

 stages

0.87

 installments

0.85

Activations Density 0.053%

occurrences of numerical sequences starting with the number "two"

occurrences of the word "two."

No Comments

No Known Activations