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

Head Attr Weights

0:0.10

1:0.06

2:0.06

3:0.09

4:0.07

5:0.09

6:0.06

7:0.07

8:0.10

9:0.08

10:0.07

11:0.08

Negative Logits

 vape

-1.78

 Handbook

-1.67

Battery

-1.66

mAh

-1.62

 Prophe

-1.55

️

-1.55

Anth

-1.54

DOM

-1.52

 Sweep

-1.52

urb

-1.51

POSITIVE LOGITS

kson

2.14

ysis

2.05

rosis

1.92

livious

1.91

xus

1.81

tch

1.81

 Krish

1.77

chuk

1.73

��

1.73

condition

1.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.