INDEX

Explanations

discussions around decision making and opinion sharing in various contexts

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

1:0.03

2:0.04

3:0.34

4:0.13

5:0.05

6:0.03

7:0.08

8:0.07

9:0.02

10:0.07

11:0.03

Negative Logits

 perfected

-2.45

ielding

-2.25

 favoured

-2.17

'),

-2.17

oufl

-2.07

 clad

-2.04

 disguised

-2.03

 discarded

-2.02

arers

-2.02

fitted

-2.02

POSITIVE LOGITS

Interview

2.80

[+

2.78

 SPORTS

2.66

Aren

2.64

CBS

2.59

JC

2.58

WOM

2.56

2.53

AMY

2.50

?:

2.49

Activations Density 0.204%

discussions around decision making and opinion sharing in various contexts

No Comments

No Known Activations