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

1:0.06

2:0.10

3:0.07

4:0.07

5:0.07

6:0.08

7:0.08

8:0.08

9:0.06

10:0.09

11:0.09

Negative Logits

 porous

-1.81

 backing

-1.70

 lucky

-1.65

 sterling

-1.65

 ounce

-1.65

 buck

-1.64

 alarmed

-1.61

lax

-1.59

 brute

-1.58

 bullish

-1.58

POSITIVE LOGITS

thood

2.26

translation

2.21

world

1.96

onomous

1.91

[[

1.84

sbm

1.84

Race

1.81

aut

1.80

issions

1.79

cone

1.78

Activations Density 0.000%

No Known Activations

This feature has no known activations.