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

0:0.09

1:0.10

2:0.08

3:0.08

4:0.07

5:0.07

6:0.07

7:0.09

8:0.09

9:0.06

10:0.07

11:0.08

Negative Logits

issions

-1.85

 carriers

-1.75

}}

-1.74

 blockers

-1.69

annels

-1.69

istors

-1.68

iders

-1.68

kees

-1.67

omes

-1.65

uations

-1.64

POSITIVE LOGITS

 Hungry

1.82

 Essex

1.75

 captivity

1.69

 Connecticut

1.66

 Creature

1.65

conn

1.62

neck

1.60

 Bernstein

1.59

 Conn

1.55

 Vienna

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.