INDEX

Explanations

references to competitive sports or performance outcomes

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

taboola

-0.92

âĢ¦]

-0.85

ONSORED

-0.81

Recomm

-0.78

Interstitial

-0.78

terday

-0.76

Reviewer

-0.75

 intimid

-0.74

PDATE

-0.73

)}

-0.72

POSITIVE LOGITS

ico

0.73

rious

0.70

cles

0.65

mid

0.63

bands

0.62

coni

0.62

gian

0.62

floor

0.61

iasm

0.61

 Bagg

0.60

Activations Density 12.725%

references to competitive sports or performance outcomes

No Comments

No Known Activations