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

1:0.09

2:0.08

3:0.08

4:0.08

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.07

11:0.07

Negative Logits

 Maximum

-1.77

Effective

-1.72

Maximum

-1.72

ま

-1.71

Lat

-1.69

 withd

-1.62

rough

-1.59

ín

-1.59

 Mellon

-1.58

 Goodman

-1.57

POSITIVE LOGITS

2.16

zees

1.98

 Covenant

1.90

kef

1.83

rir

1.77

 emancipation

1.77

slave

1.68

 ministries

1.63

 covenant

1.63

 Rivals

1.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.