INDEX

Explanations

the presence of expert references in a discussion

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

2:0.07

3:0.07

4:0.08

5:0.09

6:0.08

7:0.09

8:0.07

9:0.09

10:0.08

11:0.07

Negative Logits

raints

-3.04

 braces

-2.85

 dstg

-2.75

 welf

-2.67

 neon

-2.65

 occupational

-2.61

 microw

-2.60

Rail

-2.54

 helicop

-2.52

 heating

-2.50

POSITIVE LOGITS

 Citation

3.28

Mig

3.10

 Lorenzo

2.97

 Jarrett

2.82

 Administration

2.78

DonaldTrump

2.72

 Prophe

2.64

ogle

2.61

 Baghd

2.57

ū

2.57

Activations Density 0.000%

the presence of expert references in a discussion

No Comments

No Known Activations