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

0:0.09

1:0.07

2:0.08

3:0.08

4:0.08

5:0.07

6:0.09

7:0.08

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

 aval

-3.42

 tigers

-2.92

 gymn

-2.86

 skelet

-2.85

 buffalo

-2.72

inosaur

-2.71

 welf

-2.66

 athlet

-2.62

riad

-2.61

roy

-2.59

POSITIVE LOGITS

ONSORED

3.13

 Bridges

2.88

 Vessel

2.62

 Tone

2.60

 Lane

2.48

 Trigger

2.48

 Trap

2.46

 Hanson

2.45

 LINK

2.45

forth

2.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.