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

1:0.05

2:0.09

3:0.08

4:0.08

5:0.09

6:0.09

7:0.08

8:0.07

9:0.08

10:0.07

11:0.07

Negative Logits

amsung

-1.96

verages

-1.80

jriwal

-1.77

ctors

-1.76

verett

-1.70

═

-1.68

ARDIS

-1.68

Newsletter

-1.64

ngth

-1.60

ã

-1.58

POSITIVE LOGITS

ilation

1.58

warning

1.51

payer

1.50

urance

1.45

gro

1.41

CRC

1.37

 captivity

1.35

MMR

1.34

GCC

1.32

RPM

1.32

Activations Density 0.000%

No Known Activations

This feature has no known activations.