INDEX

Explanations

conditional phrases related to hypothetical situations and outcomes

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

0:0.06

1:0.03

2:0.07

3:0.19

4:0.02

5:0.09

6:0.02

7:0.07

8:0.03

9:0.02

10:0.34

11:0.02

Negative Logits

 progresses

-2.13

 extends

-2.03

 arrives

-1.99

 learns

-1.95

 enhances

-1.91

 improves

-1.91

 regulates

-1.86

 interacts

-1.86

 reaches

-1.84

 recovers

-1.82

POSITIVE LOGITS

would

2.13

 Would

2.11

 instantly

2.08

 surely

2.07

thinkable

2.04

 cringe

1.98

 immediately

1.89

 wouldn

1.86

wered

1.86

 ashamed

1.85

Activations Density 0.363%

conditional phrases related to hypothetical situations and outcomes

No Comments

No Known Activations