INDEX

Explanations

relational verbs associated with processes or actions

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

0:0.04

1:0.03

2:0.07

3:0.06

4:0.13

5:0.04

6:0.04

7:0.33

8:0.04

9:0.05

10:0.06

11:0.05

Negative Logits

assad

-1.58

psons

-1.57

uart

-1.45

adiq

-1.45

 assessed

-1.45

romy

-1.43

ighth

-1.42

endez

-1.40

�

-1.40

á

-1.39

POSITIVE LOGITS

wash

1.63

une

1.56

 molten

1.55

 obscurity

1.44

 intrigue

1.44

 Dialogue

1.42

 attrition

1.41

 unden

1.41

 discontent

1.40

 murky

1.39

Activations Density 0.000%

relational verbs associated with processes or actions

No Comments

No Known Activations