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

1:0.06

2:0.07

3:0.09

4:0.08

5:0.08

6:0.07

7:0.08

8:0.09

9:0.09

10:0.08

11:0.08

Negative Logits

 Zucker

-2.35

ovie

-2.07

Boe

-1.96

vier

-1.92

zos

-1.82

ohl

-1.77

 Lorenzo

-1.74

chairs

-1.73

 Pieces

-1.73

 Loren

-1.68

POSITIVE LOGITS

aniel

1.94

reshold

1.87

indu

1.78

 unsolved

1.73

 rainbow

1.68

 timestamp

1.62

 Question

1.62

 disclaim

1.57

 threshold

1.56

estamp

1.53

Activations Density 0.000%

No Known Activations

This feature has no known activations.