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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.07

1:0.05

2:0.09

3:0.09

4:0.09

5:0.07

6:0.07

7:0.08

8:0.08

9:0.08

10:0.09

11:0.08

Negative Logits

Ful

-1.82

Reloaded

-1.80

uve

-1.72

 Herz

-1.67

 Leban

-1.65

Pont

-1.65

Bio

-1.65

 Muse

-1.63

 Berman

-1.62

NetMessage

-1.55

POSITIVE LOGITS

stakes

2.00

 violation

1.81

 amnesty

1.75

 cheating

1.70

 legality

1.69

pron

1.67

 Incident

1.67

 discrepancy

1.64

uties

1.63

 Results

1.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.