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

0:0.06

1:0.07

2:0.10

3:0.09

4:0.08

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.06

11:0.08

Negative Logits

 Playboy

-1.75

 Haku

-1.71

 Beast

-1.70

 Buzz

-1.70

 Ding

-1.70

AOL

-1.68

 Mean

-1.67

 Boost

-1.66

 Slash

-1.66

 Hash

-1.64

POSITIVE LOGITS

thood

2.05

ocrates

1.99

 jails

1.94

iciary

1.85

ctuary

1.85

ethyst

1.77

sterdam

1.74

trust

1.74

ossession

1.73

packing

1.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.