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

0:0.07

1:0.07

2:0.08

3:0.07

4:0.07

5:0.09

6:0.09

7:0.08

8:0.07

9:0.09

10:0.08

11:0.08

Negative Logits

 Lever

-3.01

��

-2.79

 Regulatory

-2.62

 reviewer

-2.62

 Wonderland

-2.61

llular

-2.57

 Lean

-2.57

 Regulation

-2.56

Lur

-2.53

 Loop

-2.50

POSITIVE LOGITS

anan

2.88

Semitism

2.77

AIDS

2.76

―

2.74

aina

2.53

ysis

2.51

jen

2.50

HUD

2.50

Gaza

2.50

Sov

2.49

Activations Density 0.000%

No Known Activations

This feature has no known activations.