INDEX

Explanations

emotive language and expressions mixed with technical terms

oai_token-act-pair · gpt-3.5-turbo

occurrences of a specific character or symbol

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 promoters

-0.75

 imitation

-0.74

raviolet

-0.73

 carbohyd

-0.72

 gist

-0.69

 stake

-0.67

 plank

-0.67

 constitu

-0.65

geries

-0.64

 dossier

-0.64

POSITIVE LOGITS

ï¸ı

1.14

å¥³

1.05

Ļ

0.96

âĸĦ

0.92

ï¸

0.91

SHIP

0.89

ħ

0.88

ãĥ¥

0.87

Â£

0.86

Ľ

0.86

Activations Density 0.526%

emotive language and expressions mixed with technical terms

occurrences of a specific character or symbol

No Comments

No Known Activations