INDEX

Explanations

references to personal experiences and feelings of being overwhelmed or stressed in various situations

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

0:0.02

1:0.02

2:0.14

3:0.26

4:0.16

5:0.03

6:0.03

7:0.07

8:0.04

9:0.05

10:0.07

11:0.06

Negative Logits

 ASAP

-1.66

rum

-1.65

*:

-1.60

 momentarily

-1.54

ima

-1.51

*)

-1.51

 presumably

-1.48

 countdown

-1.46

possibly

-1.46

]'

-1.46

POSITIVE LOGITS

nor

2.88

 anymore

2.50

 whatsoever

1.90

soever

1.81

 slightest

1.79

 EVER

1.73

 Flavoring

1.61

nor

1.60

Reviewer

1.54

 ever

1.54

Activations Density 0.177%

references to personal experiences and feelings of being overwhelmed or stressed in various situations

No Comments

No Known Activations