INDEX

Explanations

phrases that indicate the transmission or impact of laws, policies, or charges on individuals and the community

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-att_32k-oai

Configuration

jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

32,768

Data Type

torch.float32

Hook Name

blocks.3.hook_attn_out

Hook Layer

Architecture

standard

Context Size

Dataset

Skylion007/openwebtext

Activation Function

topk

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Agu

-0.71

 Scare

-0.70

 haunted

-0.68

 Cage

-0.68

erella

-0.66

 Carpenter

-0.63

 Ryder

-0.62

 haunting

-0.62

 Vampire

-0.61

 clown

-0.60

POSITIVE LOGITS

doi

0.84

archive

0.83

Fax

0.79

netflix

0.78

rogens

0.78

izont

0.76

heit

0.76

PsyNetMessage

0.75

kell

0.75

RT

0.73

Activations Density 0.326%

phrases that indicate the transmission or impact of laws, policies, or charges on individuals and the community

No Comments

No Known Activations