INDEX

Explanations

discussions surrounding tax policy and its implications on different socioeconomic classes

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.16

1:0.07

2:0.06

3:0.08

4:0.08

5:0.02

6:0.16

7:0.10

8:0.02

9:0.06

10:0.05

11:0.09

Negative Logits

 mosqu

-3.65

 Moor

-3.36

Sensor

-3.23

Mos

-3.08

 disinfect

-2.82

 Forensic

-2.77

 harbour

-2.75

voy

-2.71

Seb

-2.71

 nudity

-2.71

POSITIVE LOGITS

Tax

4.97

tax

4.75

Tax

4.36

tax

4.16

 millionaires

3.91

 Treasury

3.86

CBO

3.81

 deductions

3.80

 Fiscal

3.76

 taxing

3.69

Activations Density 0.120%

discussions surrounding tax policy and its implications on different socioeconomic classes

No Comments

No Known Activations