INDEX

Explanations

quantifiable data and statistics related to various topics

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

0:0.01

1:0.03

2:0.24

3:0.23

4:0.13

5:0.05

6:0.03

7:0.05

8:0.03

9:0.03

10:0.06

11:0.06

Negative Logits

PDATE

-1.82

 endif

-1.79

srf

-1.62

ancial

-1.60

nown

-1.47

 COURT

-1.42

ADRA

-1.41

aith

-1.40

HCR

-1.39

mble

-1.38

POSITIVE LOGITS

?",

1.86

](

1.60

"],

1.56

 corpus

1.49

?,

1.43

>,

1.40

 surveyed

1.37

 denomination

1.36

],

1.34

 entrants

1.34

Activations Density 0.021%

quantifiable data and statistics related to various topics

No Comments

No Known Activations