INDEX

Explanations

phrases related to rates or quantities

oai_token-act-pair · gpt-3.5-turbo

the symbol for paragraph breaks and repeated phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

æ³

-0.86

çļ

-0.82

æĦ

-0.81

å·

-0.76

çīĪ

-0.75

 Aires

-0.74

ãĤ®

-0.74

ylum

-0.74

redients

-0.73

roots

-0.73

POSITIVE LOGITS

 occurrence

0.80

 progress

0.76

 parity

0.76

 incidence

0.75

 interest

0.75

 erosion

0.73

 electricity

0.73

 escalation

0.73

 development

0.70

 adjustment

0.70

Activations Density 0.057%

phrases related to rates or quantities

the symbol for paragraph breaks and repeated phrases

No Comments

No Known Activations