INDEX

Explanations

statements related to numeric values and statistics

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

2:0.05

3:0.04

4:0.04

5:0.04

6:0.25

7:0.02

8:0.03

9:0.26

10:0.02

11:0.04

Negative Logits

 Cabrera

-4.32

 Elys

-4.30

 McKenzie

-4.02

Bie

-3.78

AU

-3.53

Williams

-3.52

nir

-3.50

 Daniels

-3.47

\\\\

-3.47

vim

-3.45

POSITIVE LOGITS

Round

7.13

 Round

7.08

round

6.94

 round

6.94

 rounds

6.61

 Rounds

5.97

 rounding

5.12

 rounded

4.68

 oval

4.36

rounded

4.35

Activations Density 0.017%

statements related to numeric values and statistics

No Comments

No Known Activations