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

0:0.08

1:0.05

2:0.09

3:0.09

4:0.08

5:0.08

6:0.07

7:0.06

8:0.09

9:0.08

10:0.08

11:0.09

Negative Logits

selage

-1.81

etsk

-1.72

ascus

-1.65

Balt

-1.65

cox

-1.61

 helic

-1.61

pez

-1.60

 dere

-1.57

argo

-1.57

ird

-1.55

POSITIVE LOGITS

��

1.94

mbuds

1.79

utenberg

1.77

�

1.71

��

1.64

steen

1.63

��

1.54

quist

1.51

parts

1.48

IST

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.