INDEX

Explanations

the presence of the pronoun "it" and related forms

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

0:0.05

1:0.07

2:0.08

3:0.06

4:0.08

5:0.05

6:0.07

7:0.24

8:0.05

9:0.05

10:0.10

11:0.05

Negative Logits

alli

-1.87

umn

-1.85

arden

-1.80

ecided

-1.75

 supportive

-1.70

raham

-1.68

inki

-1.67

 supported

-1.65

 immersed

-1.57

enic

-1.56

POSITIVE LOGITS

��極

2.17

 Goods

1.79

 Practices

1.74

ーティ

1.68

 Burg

1.64

 Advertising

1.64

 unfocusedRange

1.61

�

1.58

 Competition

1.58

 Coup

1.58

Activations Density 0.000%

the presence of the pronoun "it" and related forms

No Comments

No Known Activations