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

1:0.07

2:0.07

3:0.08

4:0.07

5:0.08

6:0.09

7:0.07

8:0.10

9:0.08

10:0.07

11:0.08

Negative Logits

pak

-1.77

minster

-1.76

 Lumpur

-1.71

RIP

-1.61

Buk

-1.57

MH

-1.56

yg

-1.51

FAR

-1.48

osc

-1.48

Pul

-1.45

POSITIVE LOGITS

urations

1.85

"],"

1.77

 contrasts

1.60

Abstract

1.60

 distinctions

1.58

folio

1.57

 emphasizes

1.48

 counters

1.46

 stresses

1.46

 forms

1.45

Activations Density 0.000%

No Known Activations

This feature has no known activations.