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

1:0.08

2:0.08

3:0.07

4:0.07

5:0.09

6:0.07

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

endif

-2.02

cms

-1.72

QC

-1.70

 Shore

-1.65

 Silicon

-1.63

ancouver

-1.59

 Wire

-1.58

itbart

-1.56

 Cable

-1.52

 Levant

-1.52

POSITIVE LOGITS

hift

1.82

 artif

1.73

 accur

1.71

omaly

1.69

raped

1.66

thood

1.65

 lifes

1.60

 volunt

1.58

 bribe

1.56

 punishments

1.54

Activations Density 0.000%

No Known Activations

This feature has no known activations.