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

0:0.07

1:0.04

2:0.09

3:0.08

4:0.09

5:0.08

6:0.08

7:0.08

8:0.09

9:0.08

10:0.09

11:0.08

Negative Logits

 beauty

-1.78

 scoreboard

-1.78

 vanity

-1.77

 bland

-1.75

 hindsight

-1.70

 disguise

-1.69

 simplicity

-1.68

ouston

-1.64

mah

-1.62

tru

-1.60

POSITIVE LOGITS

atonin

1.95

osponsors

1.86

acteria

1.85

directed

1.85

acter

1.82

ordering

1.72

Transfer

1.71

RNA

1.67

osuke

1.66

acterial

1.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.