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

0:0.08

1:0.06

2:0.08

3:0.08

4:0.07

5:0.08

6:0.09

7:0.08

8:0.08

9:0.09

10:0.07

11:0.09

Negative Logits

edit

-1.68

 Videos

-1.65

 IMAGES

-1.60

ertodd

-1.60

Ing

-1.59

Merit

-1.58

cade

-1.55

actionDate

-1.52

�

-1.44

 Angle

-1.42

POSITIVE LOGITS

 norm

1.82

 minim

1.76

helps

1.74

ombo

1.71

ichever

1.65

fter

1.60

 semblance

1.55

 replen

1.54

 cycl

1.54

 allowance

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.