INDEX

Explanations

references to political figures, particularly the president

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.16

2:0.03

3:0.04

4:0.04

5:0.33

6:0.07

7:0.03

8:0.03

9:0.03

10:0.09

11:0.03

Negative Logits

 Manit

-1.97

 Shal

-1.91

 swast

-1.84

[&

-1.83

 stret

-1.80

,,,,

-1.78

 Staten

-1.77

 dotted

-1.75

 Marketable

-1.75

 ratios

-1.73

POSITIVE LOGITS

older

2.56

runner

2.31

ee

2.24

ender

2.05

Party

2.04

mine

2.01

�

1.99

runners

1.99

aqu

1.98

aster

1.98

Activations Density 0.000%

references to political figures, particularly the president

No Comments

No Known Activations