INDEX

Explanations

phrases related to blame or accountability in various contexts

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

acl

-0.79

Cour

-0.79

iae

-0.78

fw

-0.78

conserv

-0.76

IOR

-0.76

ower

-0.76

eeper

-0.74

ardless

-0.74

liga

-0.73

POSITIVE LOGITS

 faulty

0.72

 Cham

0.71

 Scourge

0.71

 Somali

0.70

 Bloody

0.67

 Massacre

0.66

 Dish

0.66

 lousy

0.66

 Pengu

0.65

 salv

0.64

Activations Density 0.049%

phrases related to blame or accountability in various contexts

No Comments

No Known Activations