INDEX

Explanations

recent events or updates

oai_token-act-pair · gpt-3.5-turbo

instances of the word "recent"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

İĭ

-0.78

lua

-0.75

vier

-0.72

avery

-0.72

oat

-0.71

qqa

-0.69

matic

-0.68

cius

-0.68

rice

-0.67

ñ

-0.67

POSITIVE LOGITS

 incarnation

0.94

 installment

0.86

 iteration

0.85

 episode

0.83

 edition

0.78

 installments

0.74

 episodes

0.72

 snippet

0.72

 occupant

0.71

 manifestation

0.71

Activations Density 0.012%

recent events or updates

instances of the word "recent"

No Comments

No Known Activations