INDEX

Explanations

references to specific Intel processors

oai_token-act-pair · gpt-3.5-turbo

references to Intel products and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

gery

-0.82

pee

-0.81

iatrics

-0.72

pees

-0.70

 Antar

-0.69

hirt

-0.69

bish

-0.68

glers

-0.66

geoning

-0.66

rouse

-0.66

POSITIVE LOGITS

iture

0.96

 Corporation

0.86

 Labs

0.84

Â®

0.81

 Extreme

0.81

 Xeon

0.81

Performance

0.77

omics

0.75

 processors

0.74

Intel

0.74

Activations Density 0.021%

references to specific Intel processors

references to Intel products and specifications

No Comments

No Known Activations