INDEX

Explanations

phrases relating to U.S. political affiliations and support

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

0:0.02

1:0.02

2:0.08

3:0.06

4:0.20

5:0.02

6:0.03

7:0.30

8:0.03

9:0.04

10:0.07

11:0.07

Negative Logits

missing

-1.87

knife

-1.70

trak

-1.69

rh

-1.69

ucket

-1.66

 typo

-1.59

 pear

-1.52

where

-1.52

amous

-1.49

traumatic

-1.47

POSITIVE LOGITS

 taxp

1.67

 Lauder

1.57

 superiors

1.55

 sympathetic

1.54

 Opposition

1.52

 guiName

1.51

 minorities

1.48

[*

1.47

 minority

1.44

 allied

1.44

Activations Density 0.000%

phrases relating to U.S. political affiliations and support

No Comments

No Known Activations