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

1:0.07

2:0.09

3:0.07

4:0.07

5:0.09

6:0.08

7:0.07

8:0.07

9:0.08

10:0.09

11:0.08

Negative Logits

 Seed

-2.07

 Seeds

-1.70

 vanquished

-1.68

 Juice

-1.58

 seed

-1.56

 seeds

-1.55

 Gener

-1.54

 Pepper

-1.52

Pot

-1.49

 Extract

-1.48

POSITIVE LOGITS

pole

1.95

ellen

1.73

roud

1.71

wire

1.65

BUS

1.62

 rethink

1.61

acus

1.60

veland

1.58

ampunk

1.57

externalActionCode

1.56

Activations Density 0.000%

No Known Activations

This feature has no known activations.