INDEX

Explanations

the concept of support or friendship

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

2:0.07

3:0.08

4:0.08

5:0.09

6:0.08

7:0.08

8:0.06

9:0.10

10:0.08

11:0.07

Negative Logits

 msec

-2.90

 Bloody

-2.59

REL

-2.59

DAM

-2.55

vg

-2.53

Torrent

-2.49

\.

-2.47

genre

-2.44

 Remix

-2.43

��

-2.43

POSITIVE LOGITS

ocal

2.92

psey

2.90

olor

2.79

ogn

2.68

 Schmidt

2.63

phal

2.57

 boarding

2.53

 obser

2.51

 Rockies

2.51

 Oaks

2.49

Activations Density 0.000%

the concept of support or friendship

No Comments

No Known Activations