INDEX

Explanations

references to inspections and regulatory compliance

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.16

1:0.07

2:0.05

3:0.05

4:0.08

5:0.02

6:0.21

7:0.11

8:0.02

9:0.04

10:0.07

11:0.08

Negative Logits

luaj

-2.74

 Conor

-2.68

upl

-2.58

 Crimson

-2.56

 wedd

-2.54

 Cory

-2.49

 Clash

-2.46

 Malcolm

-2.44

 Ragnarok

-2.43

 Frazier

-2.40

POSITIVE LOGITS

 inspectors

7.57

 inspections

7.02

 inspection

6.70

 Inspection

6.67

 Inspect

6.47

 inspected

6.33

 inspect

6.17

 inspector

6.04

 inspecting

5.50

 Inspector

4.86

Activations Density 0.019%

references to inspections and regulatory compliance

No Comments

No Known Activations