INDEX

Explanations

stories or information related to individuals serving in various capacities or roles

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "serving."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

alth

-0.73

imar

-0.70

opy

-0.65

 Panic

-0.65

 Freak

-0.65

TPPStreamerBot

-0.64

 Cancel

-0.64

 Drift

-0.64

 Audi

-0.63

sed

-0.63

POSITIVE LOGITS

 serving

3.70

 Serving

2.76

serving

2.44

 serve

2.09

 served

1.97

Serv

1.92

 Serve

1.85

 SERV

1.70

 serves

1.67

 servings

1.49

Activations Density 0.013%

stories or information related to individuals serving in various capacities or roles

occurrences of the word "serving."

No Comments

No Known Activations