INDEX

Explanations

stock symbols listed under NASDAQ and NYSE exchanges

oai_token-act-pair · gpt-3.5-turbo

references to NASDAQ-related entities and financial terms

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

naires

-0.90

headers

-0.72

dyl

-0.63

 surv

-0.61

 Ramadan

-0.59

ãĢĲ

-0.58

ãĥĥãĥĪ

-0.58

 impunity

-0.57

onies

-0.57

interrupted

-0.57

POSITIVE LOGITS

DAQ

2.14

daq

1.42

NAS

1.21

TY

1.02

CAR

0.99

emonic

0.92

emark

0.89

ELY

0.89

ports

0.89

pace

0.88

Activations Density 0.013%

stock symbols listed under NASDAQ and NYSE exchanges

references to NASDAQ-related entities and financial terms

No Comments

No Known Activations