INDEX

Explanations

words related to Intel processors

oai_token-act-pair · gpt-3.5-turbo

mentions of the company Intel

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Antar

-0.78

gery

-0.76

pee

-0.74

 Roose

-0.72

rouse

-0.71

hirt

-0.67

geoning

-0.67

iatrics

-0.67

othy

-0.66

ashington

-0.65

POSITIVE LOGITS

iture

0.88

Intel

0.86

 Intel

0.84

 Xeon

0.84

 processors

0.80

intel

0.80

 chipset

0.77

 Labs

0.76

 CPUs

0.76

Â®

0.76

Activations Density 0.005%

words related to Intel processors

mentions of the company Intel

No Comments

No Known Activations