INDEX

Explanations

proper acronyms related to research organizations and technologies

oai_token-act-pair · gpt-3.5-turbo

ubiquitous references to the acronym "RI."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

forth

-0.76

wagon

-0.76

kinson

-0.74

terson

-0.69

 delay

-0.69

nesium

-0.69

rules

-0.69

lein

-0.68

dayName

-0.67

icians

-0.66

POSITIVE LOGITS

Äĩ

0.96

YA

0.95

KER

0.93

VEN

0.92

ving

0.90

ASON

0.89

ECA

0.84

estinal

0.83

BE

0.83

PS

0.83

Activations Density 0.014%

proper acronyms related to research organizations and technologies

ubiquitous references to the acronym "RI."

No Comments

No Known Activations