INDEX

Explanations

names of political parties and movements

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

0:0.06

1:0.13

2:0.03

3:0.04

4:0.04

5:0.30

6:0.03

7:0.02

8:0.03

9:0.06

10:0.13

11:0.07

Negative Logits

nown

-1.72

 aval

-1.63

 extingu

-1.59

 accommodation

-1.58

 rearr

-1.58

 dele

-1.51

 invol

-1.51

 CrossRef

-1.50

eas

-1.47

 detain

-1.43

POSITIVE LOGITS

Party

2.32

 Party

2.31

 Voters

2.30

Vote

2.28

Democrats

2.23

Republicans

2.11

 Democrats

2.07

 Conservatives

2.05

 Dems

2.01

party

2.00

Activations Density 0.007%

names of political parties and movements

No Comments

No Known Activations