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

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.08

10:0.07

11:0.09

Negative Logits

���

-2.09

�

-1.91

�

-1.86

Gad

-1.78

NFC

-1.78

 Bots

-1.75

 Hispanics

-1.75

BLIC

-1.71

anooga

-1.69

�

-1.69

POSITIVE LOGITS

[+

1.85

 Leaves

1.78

osponsors

1.75

 ferment

1.74

 fragrance

1.73

arij

1.72

coat

1.70

 PACK

1.68

lik

1.65

apy

1.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.