INDEX

Explanations

occurrences of specific characters or symbols in the text

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

0:0.07

1:0.07

2:0.08

3:0.07

4:0.08

5:0.08

6:0.09

7:0.08

8:0.09

9:0.07

10:0.08

11:0.08

Negative Logits

IPM

-3.07

 arrang

-2.68

byn

-2.66

PH

-2.62

 Phen

-2.47

 Zion

-2.46

HI

-2.45

 Torn

-2.41

 Parsons

-2.40

Xi

-2.39

POSITIVE LOGITS

philis

3.05

��極

2.77

{*

2.69

interstitial

2.64

 coli

2.63

―

2.63

 Mara

2.58

¢

2.56

gradation

2.52

uration

2.46

Activations Density 0.000%

occurrences of specific characters or symbols in the text

No Comments

No Known Activations