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

1:0.06

2:0.09

3:0.08

4:0.09

5:0.07

6:0.09

7:0.09

8:0.08

9:0.08

10:0.09

11:0.07

Negative Logits

rylic

-2.08

andowski

-1.83

 Franch

-1.67

lectic

-1.65

uggets

-1.58

uten

-1.55

atti

-1.54

 soph

-1.53

 polarized

-1.51

 Dupl

-1.50

POSITIVE LOGITS

 Debug

1.80

untarily

1.67

 Runs

1.66

 Ignore

1.60

successfully

1.57

monitor

1.57

inet

1.52

anamo

1.51

Aid

1.50

 Unfortunately

1.48

Activations Density 0.000%

No Known Activations

This feature has no known activations.