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

1:0.06

2:0.09

3:0.09

4:0.09

5:0.08

6:0.07

7:0.08

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

エ

-2.17

behind

-1.89

Sil

-1.77

ゼ

-1.66

Stock

-1.60

サ

-1.60

Oo

-1.58

 Ally

-1.53

 Chong

-1.51

Ak

-1.50

POSITIVE LOGITS

ividual

1.99

 loads

1.97

 weights

1.81

itton

1.79

 circulation

1.77

 numbering

1.75

 workload

1.64

uge

1.64

 sampling

1.63

umers

1.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.