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

1:0.15

2:0.08

3:0.07

4:0.07

5:0.07

6:0.07

7:0.07

8:0.08

9:0.07

10:0.07

11:0.08

Negative Logits

irements

-1.78

odder

-1.71

 Libre

-1.63

ohm

-1.63

omics

-1.63

 Stadium

-1.62

pton

-1.59

 Fiat

-1.57

 Mend

-1.55

 Signal

-1.53

POSITIVE LOGITS

神

1.91

 enthusi

1.75

plet

1.73

 Reincarn

1.71

 repentance

1.69

PTS

1.66

 PACK

1.62

 FUCK

1.62

 sinners

1.54

HAHA

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.