INDEX

Explanations

terms related to scoring and political measures

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.04

2:0.03

3:0.04

4:0.04

5:0.04

6:0.03

7:0.09

8:0.03

9:0.10

10:0.03

11:0.39

Negative Logits

Owner

-2.32

 supervision

-2.30

ourcing

-2.21

 Situation

-2.17

 Environment

-2.17

 Presence

-2.15

glers

-2.14

 circumstance

-2.11

 habitat

-2.03

 machinery

-2.02

POSITIVE LOGITS

points

2.95

 points

2.90

 Nobel

2.64

 goals

2.55

Points

2.47

pts

2.42

 Points

2.32

 Solitaire

2.20

 Grail

2.17

ometric

2.17

Activations Density 0.009%

terms related to scoring and political measures

No Comments

No Known Activations