INDEX

Explanations

words related to software technologies, particularly databases like PostgreSQL and MongoDB

oai_token-act-pair · gpt-3.5-turbo

references to specific technology stacks and databases

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

inges

-0.73

ãĥ£

-0.65

ble

-0.63

neys

-0.62

taboola

-0.61

 AMER

-0.60

hend

-0.60

KT

-0.59

 FEMA

-0.59

ographed

-0.58

POSITIVE LOGITS

Â®,

0.85

Â®

0.85

 Architecture

0.81

API

0.80

Wiki

0.79

Client

0.78

Sharp

0.78

Ware

0.76

 Reloaded

0.75

ModLoader

0.75

Activations Density 0.113%

words related to software technologies, particularly databases like PostgreSQL and MongoDB

references to specific technology stacks and databases

No Comments

No Known Activations