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

1:0.05

2:0.09

3:0.06

4:0.10

5:0.08

6:0.09

7:0.08

8:0.09

9:0.07

10:0.07

11:0.08

Negative Logits

EVs

-1.86

NX

-1.86

 Offline

-1.80

 belie

-1.77

 habitable

-1.70

 redes

-1.69

selves

-1.65

 veter

-1.65

tein

-1.65

STD

-1.61

POSITIVE LOGITS

laughter

2.29

managed

1.83

rir

1.82

laugh

1.81

rette

1.76

monkey

1.75

agogue

1.74

cl

1.74

wash

1.73

ti

1.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.