INDEX

Explanations

terms related to programming concepts, specifically references in code

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

1:0.08

2:0.08

3:0.07

4:0.08

5:0.07

6:0.10

7:0.07

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

 Petraeus

-3.15

Obama

-3.11

isSpecialOrderable

-3.01

Romney

-2.76

 Arpaio

-2.67

Arizona

-2.62

PRES

-2.62

Versions

-2.58

politics

-2.58

 affirmative

-2.57

POSITIVE LOGITS

 Maiden

2.93

 swarm

2.68

 twitch

2.62

BL

2.58

 clut

2.56

ft

2.55

%%

2.55

FB

2.53

 Fell

2.46

LET

2.46

Activations Density 0.000%

terms related to programming concepts, specifically references in code

No Comments

No Known Activations