INDEX

Explanations

expressions of approval or positivity

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

1:0.04

2:0.17

3:0.05

4:0.08

5:0.05

6:0.04

7:0.08

8:0.19

9:0.04

10:0.06

11:0.06

Negative Logits

oult

-1.84

dit

-1.66

affe

-1.62

 rotated

-1.56

Dir

-1.56

umbn

-1.54

 skelet

-1.52

pron

-1.51

kid

-1.47

ktop

-1.47

POSITIVE LOGITS

formance

1.54

TPP

1.49

Failure

1.45

imize

1.41

ARM

1.39

grave

1.38

 stronger

1.38

lasting

1.37

 worse

1.37

 inaction

1.36

Activations Density 0.000%

expressions of approval or positivity

No Comments

No Known Activations