INDEX

Explanations

references to time or temporal aspects

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

0:0.08

1:0.07

2:0.08

3:0.09

4:0.08

5:0.08

6:0.08

7:0.07

8:0.07

9:0.08

10:0.08

11:0.09

Negative Logits

 crawled

-3.00

 crawl

-2.88

 crawling

-2.80

 cracked

-2.79

 stal

-2.75

 cracking

-2.58

 patched

-2.57

 stubborn

-2.57

 amazingly

-2.57

 unravel

-2.56

POSITIVE LOGITS

iannopoulos

3.19

isites

2.87

IU

2.79

IU

2.76

ograp

2.74

tarians

2.72

gans

2.67

esan

2.67

UA

2.67

DAQ

2.67

Activations Density 0.000%

references to time or temporal aspects

No Comments

No Known Activations