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

IFrame

Link

Head Attr Weights

0:0.07

1:0.07

2:0.09

3:0.08

4:0.08

5:0.08

6:0.07

7:0.10

8:0.08

9:0.06

10:0.07

11:0.09

Negative Logits

 Qiao

-1.71

 Blanc

-1.66

 Pens

-1.60

 Fighters

-1.51

verning

-1.50

 Mens

-1.46

phas

-1.44

 chairs

-1.39

Bob

-1.36

naires

-1.35

POSITIVE LOGITS

 tide

1.66

entimes

1.61

scene

1.59

gradation

1.57

 Investig

1.55

callback

1.48

grad

1.48

iod

1.48

 guiActiveUn

1.46

inventoryQuantity

1.44

Activations Density 0.000%

No Known Activations

This feature has no known activations.