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

3:0.09

4:0.09

5:0.06

6:0.07

7:0.08

8:0.08

9:0.10

10:0.08

11:0.09

Negative Logits

iasis

-1.79

 nutshell

-1.55

senal

-1.52

 Cosponsors

-1.50

��

-1.50

 dossier

-1.47

Poc

-1.45

�

-1.44

 dece

-1.41

 subur

-1.39

POSITIVE LOGITS

cedes

1.78

 answ

1.73

Sov

1.72

.<

1.66

nil

1.65

within

1.60

Eventually

1.58

edIn

1.54

LEASE

1.54

lier

1.52

Activations Density 0.000%

No Known Activations

This feature has no known activations.