INDEX

Explanations

elements related to cooking instructions and ingredient lists

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.10.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.25

1:0.06

2:0.05

3:0.05

4:0.04

5:0.04

6:0.04

7:0.15

8:0.02

9:0.04

10:0.12

11:0.08

Negative Logits

 psychiat

-3.02

 bitcoin

-3.01

DPR

-2.91

 DPRK

-2.81

 miners

-2.75

 Exxon

-2.74

 Oswald

-2.74

 Coinbase

-2.71

 Lyme

-2.70

isons

-2.69

POSITIVE LOGITS

 pasta

6.58

 spaghetti

5.76

 noodles

4.80

 Parm

4.42

aghetti

3.91

 nood

3.90

chini

3.84

 Tomato

3.63

agna

3.62

 Sicily

3.62

Activations Density 0.005%

elements related to cooking instructions and ingredient lists

No Comments

No Known Activations