INDEX

Explanations

references to the name "Monica"

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Monica."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

minist

-0.82

ACTED

-0.76

ngth

-0.74

èĥ

-0.74

umbn

-0.73

stood

-0.72

ahead

-0.72

nings

-0.70

Trend

-0.68

TOP

-0.68

POSITIVE LOGITS

 Boulevard

0.82

 Blvd

0.80

zilla

0.72

 Monica

0.72

 Lumpur

0.71

 Grill

0.70

 Beach

0.69

zona

0.67

 Pier

0.67

 Sachs

0.65

Activations Density 0.008%

references to the name "Monica"

mentions of the name "Monica."

No Comments

No Known Activations