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

2:0.07

3:0.07

4:0.10

5:0.08

6:0.07

7:0.08

8:0.07

9:0.08

10:0.10

11:0.08

Negative Logits

 offending

-1.65

lessly

-1.57

 ********************************

-1.56

 unavoidable

-1.52

 indisc

-1.52

 safely

-1.51

eware

-1.51

ardless

-1.51

 containing

-1.46

uously

-1.45

POSITIVE LOGITS

Flight

2.08

shapeshifter

1.76

GPU

1.72

�

1.68

rists

1.67

 Robotics

1.66

Interest

1.66

rius

1.62

 Dynamics

1.61

mosp

1.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.