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

0:0.05

1:0.01

2:0.14

3:0.17

4:0.15

5:0.03

6:0.04

7:0.02

8:0.06

9:0.04

10:0.11

11:0.11

Negative Logits

gently

-1.94

anwhile

-1.90

til

-1.86

cause

-1.82

":"/

-1.75

cture

-1.73

 COURT

-1.68

bc

-1.65

rete

-1.59

rotein

-1.57

POSITIVE LOGITS

��

1.94

 clich

1.68

 nightmares

1.62

 Flan

1.62

 distractions

1.56

 fabrication

1.55

 realities

1.54

 circus

1.53

 conventions

1.52

 calcul

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.