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

2:0.08

3:0.07

4:0.08

5:0.09

6:0.09

7:0.08

8:0.08

9:0.07

10:0.08

11:0.09

Negative Logits

lex

-1.64

stall

-1.61

numbered

-1.60

chers

-1.60

neck

-1.57

paces

-1.57

depending

-1.54

say

-1.54

packing

-1.51

ident

-1.50

POSITIVE LOGITS

wcsstore

1.72

sonian

1.70

GIF

1.66

��

1.63

��

1.62

umbn

1.61

 Kappa

1.52

 Ammo

1.48

 Ragnar

1.47

ゴン

1.47

Activations Density 0.000%

No Known Activations

This feature has no known activations.