INDEX

Explanations

the word "t"

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.06

1:0.13

2:0.08

3:0.08

4:0.07

5:0.08

6:0.07

7:0.06

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

thood

-1.96

boys

-1.86

bryce

-1.68

girls

-1.66

objects

-1.63

heads

-1.61

flies

-1.58

thumbnails

-1.57

anners

-1.57

ragon

-1.56

POSITIVE LOGITS

 Marriott

1.80

 Maximum

1.55

 Mbps

1.51

QC

1.50

allo

1.44

 Intercept

1.43

 wrench

1.41

 Metro

1.38

itto

1.36

 revised

1.35

Activations Density 0.000%

the word "t"

No Comments

No Known Activations