INDEX

Explanations

references to political topics, particularly elections

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

0:0.09

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.06

7:0.08

8:0.08

9:0.09

10:0.09

11:0.08

Negative Logits

 declined

-2.49

ASC

-2.44

bleacher

-2.39

ciating

-2.39

 Schro

-2.31

 questioned

-2.31

 oppos

-2.29

 NAACP

-2.22

 plummeted

-2.21

eele

-2.20

POSITIVE LOGITS

Io

2.92

 Magicka

2.83

fw

2.75

gpu

2.74

oi

2.65

LV

2.64

Lua

2.62

Fu

2.60

%%%%

2.53

Lua

2.43

Activations Density 0.000%

references to political topics, particularly elections

No Comments

No Known Activations