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

0:0.08

1:0.06

2:0.08

3:0.09

4:0.07

5:0.08

6:0.08

7:0.08

8:0.07

9:0.07

10:0.09

11:0.08

Negative Logits

 Gaming

-1.74

 adore

-1.69

 Spectrum

-1.59

 Milky

-1.59

 Nature

-1.56

Ni

-1.54

 Parade

-1.49

 Entertainment

-1.46

 Eyes

-1.46

igion

-1.46

POSITIVE LOGITS

ifully

1.85

efficient

1.81

 clauses

1.72

nown

1.68

 certs

1.67

effective

1.65

 simulations

1.60

term

1.60

method

1.55

withstanding

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.