INDEX

Explanations

No Explanations Found

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

3:0.08

4:0.08

5:0.08

6:0.09

7:0.07

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 Johann

-3.04

 colony

-3.03

 archaeological

-2.95

 colonies

-2.71

 galactic

-2.70

 Xuan

-2.69

 annex

-2.69

 Ricardo

-2.67

 archae

-2.63

 plateau

-2.57

POSITIVE LOGITS

 Fired

3.08

Honest

2.88

milo

2.81

Style

2.79

 Respons

2.69

Snake

2.67

 Clicker

2.65

soType

2.64

Role

2.61

Weak

2.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.