INDEX

Explanations

technical terms related to deployment

oai_token-act-pair · gpt-3.5-turbo

instances of the word "deploy" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

@@@@

-0.86

iasis

-0.75

bread

-0.75

omial

-0.69

neg

-0.69

 Frie

-0.68

@@@@@@@@

-0.67

 Eater

-0.65

ago

-0.65

tha

-0.65

POSITIVE LOGITS

 deployments

0.89

 Deploy

0.88

Deploy

0.87

 deployment

0.83

ploy

0.82

aware

0.79

ables

0.79

 automation

0.77

 deployed

0.76

avorite

0.76

Activations Density 0.010%

technical terms related to deployment

instances of the word "deploy" and its variations

No Comments

No Known Activations