INDEX

Explanations

references to programming concepts, specifically function calls and parameters

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.09

3:0.09

4:0.07

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

RNA

-2.71

atin

-2.66

 offic

-2.64

 millenn

-2.64

��

-2.60

tera

-2.59

actionDate

-2.56

 radiator

-2.47

EMA

-2.47

 param

-2.47

POSITIVE LOGITS

ucket

2.63

guyen

2.59

 Burns

2.56

imgur

2.55

�

2.54

 Solo

2.53

 Dunk

2.52

 unfocused

2.50

 Lowe

2.49

 Nguyen

2.49

Activations Density 0.000%

references to programming concepts, specifically function calls and parameters

No Comments

No Known Activations