INDEX

Explanations

negative sentiment words associated with experiences and evaluations

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

0:0.12

1:0.30

2:0.03

3:0.04

4:0.03

5:0.20

6:0.03

7:0.03

8:0.05

9:0.05

10:0.04

11:0.03

Negative Logits

ギ

-1.92

 Sear

-1.81

 Refer

-1.81

�

-1.78

 refer

-1.75

AE

-1.75

�

-1.72

 Rowe

-1.69

 DRAG

-1.65

 referring

-1.64

POSITIVE LOGITS

Enough

2.35

enough

2.30

�

2.27

 Enough

2.19

 enough

2.01

PT

1.75

 sufficient

1.74

sufficient

1.72

 Parenthood

1.72

Interstitial

1.69

Activations Density 0.001%

negative sentiment words associated with experiences and evaluations

No Comments

No Known Activations