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

0:0.07

1:0.12

2:0.07

3:0.09

4:0.08

5:0.07

6:0.06

7:0.06

8:0.10

9:0.09

10:0.07

11:0.07

Negative Logits

 Marriott

-2.15

olulu

-1.69

 impression

-1.63

imon

-1.61

QC

-1.54

 seriousness

-1.54

 unspecified

-1.54

 documentation

-1.52

 Sett

-1.51

 Lowell

-1.51

POSITIVE LOGITS

osate

1.95

area

1.79

hook

1.72

 kindred

1.72

trigger

1.72

baugh

1.71

LCS

1.69

incial

1.68

stick

1.66

aceous

1.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.