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

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.07

2:0.08

3:0.08

4:0.08

5:0.08

6:0.07

7:0.08

8:0.08

9:0.09

10:0.07

11:0.07

Negative Logits

 extremes

-1.60

 approximation

-1.58

neb

-1.57

 deity

-1.55

 principle

-1.49

 championships

-1.46

 opponent

-1.45

 playoffs

-1.44

 float

-1.44

mat

-1.44

POSITIVE LOGITS

cd

1.78

haus

1.72

eligible

1.72

helle

1.71

reviewed

1.69

pd

1.64

pine

1.64

ivo

1.62

aylor

1.62

jected

1.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.