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

0:0.06

1:0.07

2:0.08

3:0.09

4:0.08

5:0.08

6:0.08

7:0.08

8:0.09

9:0.06

10:0.10

11:0.08

Negative Logits

jun

-1.66

wcs

-1.61

 Saunders

-1.59

 Rubio

-1.56

ospons

-1.52

 Schumer

-1.52

cause

-1.51

-1.50

google

-1.47

ause

-1.47

POSITIVE LOGITS

efficients

1.99

 negatives

1.71

mates

1.59

amins

1.56

ild

1.56

leaning

1.56

erve

1.55

atron

1.54

itia

1.53

Untitled

1.51

Activations Density 0.000%

No Known Activations

This feature has no known activations.