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

0:0.10

1:0.06

2:0.07

3:0.08

4:0.08

5:0.09

6:0.09

7:0.06

8:0.08

9:0.08

10:0.08

11:0.07

Negative Logits

 Architects

-2.01

��

-1.75

unity

-1.69

 decentral

-1.63

 Values

-1.58

 Reson

-1.55

amd

-1.53

 Voter

-1.53

 Invalid

-1.51

 Elemental

-1.51

POSITIVE LOGITS

cler

1.74

 Simpsons

1.52

 unwitting

1.52

 Sachs

1.49

Les

1.47

plet

1.44

cise

1.44

 Schmidt

1.43

ograp

1.42

 deliveries

1.42

Activations Density 0.000%

No Known Activations

This feature has no known activations.