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

0:0.08

1:0.04

2:0.09

3:0.08

4:0.09

5:0.07

6:0.08

7:0.08

8:0.10

9:0.07

10:0.08

11:0.08

Negative Logits

 fuss

-1.94

orum

-1.81

 budget

-1.74

actionDate

-1.66

-1.65

��

-1.63

rieg

-1.55

othal

-1.54

 throats

-1.54

"]=>

-1.47

POSITIVE LOGITS

cas

1.53

idelity

1.42

eval

1.40

 Converted

1.35

 Intermediate

1.34

 poisonous

1.34

ocating

1.33

 unhealthy

1.31

 uncom

1.31

nova

1.31

Activations Density 0.000%

No Known Activations

This feature has no known activations.