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

2:0.09

3:0.08

4:0.09

5:0.08

6:0.08

7:0.06

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

 Equipment

-2.00

 Household

-1.78

 Construction

-1.68

Home

-1.66

 furthermore

-1.65

 Death

-1.64

Uni

-1.63

 Telephone

-1.62

home

-1.62

 Humans

-1.62

POSITIVE LOGITS

severe

1.90

FontSize

1.83

 scathing

1.80

hemy

1.78

 paralysis

1.77

 hesitation

1.73

zed

1.70

Marginal

1.69

 prelim

1.69

raq

1.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.