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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.07

2:0.08

3:0.08

4:0.10

5:0.07

6:0.08

7:0.10

8:0.08

9:0.08

10:0.07

11:0.06

Negative Logits

 electroly

-1.77

 attrition

-1.67

"]=>

-1.65

.–

-1.59

 Refresh

-1.58

plings

-1.57

.")

-1.51

 screenings

-1.50

 graft

-1.50

)</

-1.50

POSITIVE LOGITS

Discussion

2.11

Sounds

1.69

Mot

1.66

 Thoughts

1.64

CONCLUS

1.58

 Hearing

1.58

GG

1.57

ゴ

1.52

Gu

1.51

shock

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.