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

0:0.12

1:0.09

2:0.09

3:0.07

4:0.06

5:0.07

6:0.07

7:0.04

8:0.08

9:0.15

10:0.05

11:0.07

Negative Logits

 hosp

-1.81

 sooner

-1.74

]."

-1.68

 goblin

-1.67

 vacancy

-1.64

 beds

-1.61

Zh

-1.61

].

-1.57

wb

-1.57

 pulp

-1.54

POSITIVE LOGITS

esty

2.07

イト

1.98

sie

1.95

akes

1.94

oras

1.87

atures

1.86

サ

1.76

ゼウス

1.75

�

1.73

alam

1.72

Activations Density 0.000%

No Known Activations

This feature has no known activations.