INDEX

Explanations

instances of the word "that."

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

0:0.11

1:0.16

2:0.03

3:0.04

4:0.03

5:0.25

6:0.03

7:0.03

8:0.06

9:0.07

10:0.07

11:0.05

Negative Logits

版

-1.79

assetsadobe

-1.77

 istg

-1.62

 photoc

-1.57

 suspended

-1.56

 disav

-1.51

 intermedi

-1.50

 telev

-1.49

 wrists

-1.49

 swast

-1.46

POSITIVE LOGITS

col

2.03

hing

1.89

________________

1.82

rez

1.81

zy

1.79

1.76

SPONSORED

1.76

Dar

1.75

·

1.74

Activations Density 0.004%

instances of the word "that."

No Comments

No Known Activations