INDEX

Explanations

questions, particularly at the end of declarative statements

oai_token-act-pair · gpt-3.5-turbo

temporal references and sequences related to events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

adian

-0.71

iosyncr

-0.70

ulnerable

-0.69

ebted

-0.65

ocative

-0.65

ãģį

-0.62

omics

-0.62

 poses

-0.61

âĦ¢

-0.61

born

-0.61

POSITIVE LOGITS

 Korra

0.77

 Luffy

0.75

 organisers

0.74

 THEY

0.73

 they

0.72

 Zhou

0.72

 Dumbledore

0.71

 nobody

0.71

 Speedway

0.71

upon

0.70

Activations Density 1.002%

questions, particularly at the end of declarative statements

temporal references and sequences related to events

No Comments

No Known Activations