INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

3:0.07

4:0.07

5:0.08

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

luaj

-1.89

undreds

-1.89

 brightest

-1.85

taboola

-1.82

 Typhoon

-1.75

 fireball

-1.75

Reviewer

-1.70

 tuned

-1.68

CVE

-1.65

asionally

-1.65

POSITIVE LOGITS

 Expend

1.78

 Conspiracy

1.68

 Surve

1.67

 Heist

1.67

 Payment

1.66

 Household

1.62

 Residential

1.61

 Coalition

1.55

 Gamer

1.54

 Adventure

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.