INDEX

Explanations

negative expressions or phrases

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

0:0.06

1:0.06

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.09

8:0.07

9:0.09

10:0.08

11:0.07

Negative Logits

 causation

-1.88

Reviewer

-1.87

══

-1.83

 monarch

-1.75

 wiser

-1.71

 monarchy

-1.70

 endeavour

-1.70

 whichever

-1.70

 blame

-1.65

 sovere

-1.64

POSITIVE LOGITS

ebin

2.00

redited

1.75

CVE

1.72

usp

1.65

inates

1.63

 Trash

1.62

dropping

1.62

affiliated

1.61

esan

1.61

covered

1.60

Activations Density 0.000%

negative expressions or phrases

No Comments

No Known Activations