INDEX

Explanations

proper nouns related to locations or organizations that contain unusual characters

oai_token-act-pair · gpt-3.5-turbo

mentions of locations and events associated with them

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 pleas

-0.79

 sacrific

-0.75

 synerg

-0.71

 gains

-0.69

 carbohyd

-0.69

 fortun

-0.68

 modifiers

-0.67

 positives

-0.67

 grit

-0.67

 multiplier

-0.67

POSITIVE LOGITS

ï¸ı

1.04

iversary

0.89

orld

0.89

nai

0.87

River

0.87

town

0.86

Town

0.85

University

0.85

City

0.84

venue

0.83

Activations Density 0.214%

proper nouns related to locations or organizations that contain unusual characters

mentions of locations and events associated with them

No Comments

No Known Activations